SKILLEMALL.ai
GitHub ↗ RU Sign in

FD agent-defender

Agent Defender - AI智能体安全防护平台。静态扫描+运行时防护+DLP脱敏。触发：(1)扫描Skill (2)启动防护 (3)DLP检测 (4)安全审计

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: caidongyun v1.0.0 MIT-0 80 files · 2 scripts body ≈ 146 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process D 38/100 · Unfinished process — weak spots: steps, result and completion, when it triggers

ReferenceAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
26/100
safety, quality, tests
Safety 60%
0
Quality 40%
66
Run on models
none yet
Process rating
D
38/100
Unfinished process
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Secrets in code medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

Instruction override medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 63

  • high Dangerous commands cmd-pipe-to-shell integrated_rules/RULES_INDEX.yaml:355
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    - description: 检测 curl | bash 模式的远程代码执行
  • high Dangerous commands cmd-pipe-to-shell integrated_rules/RULES_INDEX.yaml:357
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    name: 检测 curl | bash 模式的远程代码执行
Medium and low: 61
  • medium Dangerous commands cmd-pipe-to-shell integrated_rules/integrated_rules.json:326
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    ".*wget|sh.*",
    code literal
  • medium Exfiltration intent-browser-credential-store integrated_rules/integrated_rules.json:872
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：凭证窃取检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、云凭证、浏览器密码、密钥链窃取\n\nrule Credential_SSH_Key {\n    meta:\n        description = \"检测 SSH 密钥窃取\"\n        author = \"security-sa
    detector
  • medium Secrets in code secret-private-key integrated_rules/integrated_rules.json:900
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Secrets in code secret-private-key integrated_rules/integrated_rules.json:901
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header2 = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Exfiltration exfil-read-secret-files integrated_rules/integrated_rules.json:907
    Reads credential / secret files (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Exfiltration intent-browser-credential-store integrated_rules/integrated_rules.json:907
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Secrets in code secret-private-key integrated_rules/integrated_rules.json:907
    Private key material (detector / deny-list definition; key header without key body)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detectorheader only
  • medium Dangerous commands cmd-pipe-to-shell integrated_rules/integrated_rules.json:1113
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    "name": "检测 curl | bash 模式的远程代码执行",
    code literal
  • medium Dangerous commands cmd-pipe-to-shell integrated_rules/integrated_rules.json:1135
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)
    "raw_rule": "// YARA 规则：远程加载执行检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：curl|bash, wget|bash, PowerShell IEX, Python urllib+exec\n\nrule Remote_Exec_Curl_Bash {\n    meta:\n        description = \"检测 cur
    detector
  • medium Instruction override en-ignore-previous INTEGRATION_REPORT.md:125
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    "selection": ["ignore previous instructions"],
    detector
  • medium Instruction override en-ignore-previous INTEGRATION_REPORT.md:136
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    "patterns": [".*ignore previous instructions.*"],
    detector
  • medium Instruction override en-ignore-previous README_SIGMA_YARA.md:74
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    - "ignore previous instructions"
    quoted
  • medium Instruction override en-ignore-previous README_SIGMA_YARA.md:88
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    "patterns": [".*ignore previous instructions.*", ".*disregard all safety.*"],
    detector
  • medium Exfiltration intent-browser-credential-store rules_backup/backup_20260407_195520/credential_theft_integrated.json:28
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：凭证窃取检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、云凭证、浏览器密码、密钥链窃取\n\nrule Credential_SSH_Key {\n    meta:\n        description = \"检测 SSH 密钥窃取\"\n        author = \"security-sa
    detector
  • medium Secrets in code secret-private-key rules_backup/backup_20260407_195520/data_exfil_integrated.json:24
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Secrets in code secret-private-key rules_backup/backup_20260407_195520/data_exfil_integrated.json:25
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header2 = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Exfiltration exfil-read-secret-files rules_backup/backup_20260407_195520/data_exfil_integrated.json:31
    Reads credential / secret files (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Exfiltration intent-browser-credential-store rules_backup/backup_20260407_195520/data_exfil_integrated.json:31
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Secrets in code secret-private-key rules_backup/backup_20260407_195520/data_exfil_integrated.json:31
    Private key material (detector / deny-list definition; key header without key body)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detectorheader only
  • medium Dangerous commands cmd-pipe-to-shell rules_backup/backup_20260407_195520/remote_load_integrated.json:8
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    "name": "检测 curl | bash 模式的远程代码执行",
    code literal
  • medium Dangerous commands cmd-pipe-to-shell rules_backup/backup_20260407_195520/remote_load_integrated.json:30
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)
    "raw_rule": "// YARA 规则：远程加载执行检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：curl|bash, wget|bash, PowerShell IEX, Python urllib+exec\n\nrule Remote_Exec_Curl_Bash {\n    meta:\n        description = \"检测 cur
    detector
  • medium Dangerous commands cmd-pipe-to-shell rules_backup/backup_20260407_195520/unknown_integrated.json:319
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    ".*wget|sh.*",
    code literal
  • medium Exfiltration intent-browser-credential-store rules_backup/backup_20260407_195535/credential_theft_integrated.json:28
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：凭证窃取检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、云凭证、浏览器密码、密钥链窃取\n\nrule Credential_SSH_Key {\n    meta:\n        description = \"检测 SSH 密钥窃取\"\n        author = \"security-sa
    detector
  • medium Secrets in code secret-private-key rules_backup/backup_20260407_195535/data_exfil_integrated.json:24
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Secrets in code secret-private-key rules_backup/backup_20260407_195535/data_exfil_integrated.json:25
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header2 = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Exfiltration exfil-read-secret-files rules_backup/backup_20260407_195535/data_exfil_integrated.json:31
    Reads credential / secret files (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Exfiltration intent-browser-credential-store rules_backup/backup_20260407_195535/data_exfil_integrated.json:31
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Secrets in code secret-private-key rules_backup/backup_20260407_195535/data_exfil_integrated.json:31
    Private key material (detector / deny-list definition; key header without key body)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detectorheader only
  • medium Exfiltration intent-browser-credential-store rules/credential_theft_integrated.json:28
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：凭证窃取检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、云凭证、浏览器密码、密钥链窃取\n\nrule Credential_SSH_Key {\n    meta:\n        description = \"检测 SSH 密钥窃取\"\n        author = \"security-sa
    detector
  • medium Secrets in code secret-private-key rules/data_exfil_integrated.json:24
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Secrets in code secret-private-key rules/data_exfil_integrated.json:25
    Private key material (key header without key body; quoted — discussed, not commanded)
    "$ssh_header2 = \"-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Exfiltration exfil-read-secret-files rules/data_exfil_integrated.json:31
    Reads credential / secret files (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Exfiltration intent-browser-credential-store rules/data_exfil_integrated.json:31
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detector
  • medium Secrets in code secret-private-key rules/data_exfil_integrated.json:31
    Private key material (detector / deny-list definition; key header without key body)
    "raw_rule": "// YARA 规则：数据窃取外传检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：SSH 密钥、AWS 凭证、浏览器数据、环境变量窃取\n\nrule SSH_Key_Exfiltration {\n    meta:\n        description = \"检测 SSH 密钥窃取行为\"\n        author = \"s
    detectorheader only
  • medium Dangerous commands cmd-pipe-to-shell rules/remote_load_integrated.json:8
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    "name": "检测 curl | bash 模式的远程代码执行",
    code literal
  • medium Dangerous commands cmd-pipe-to-shell rules/remote_load_integrated.json:30
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)
    "raw_rule": "// YARA 规则：远程加载执行检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：curl|bash, wget|bash, PowerShell IEX, Python urllib+exec\n\nrule Remote_Exec_Curl_Bash {\n    meta:\n        description = \"检测 cur
    detector
  • medium Dangerous commands cmd-pipe-to-shell rules/unknown_integrated.json:319
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    ".*wget|sh.*",
    code literal
  • low Dangerous commands cmd-background-process defenderctl.sh:65
    Starts a background / autostarted process
    nohup python3 "$RESEARCH_DAEMON" > "$LOG_FILE" 2>&1 &
  • low Dangerous commands cmd-pipe-to-shell integrated_rules/integrated_rules.json:325
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)
    ".*curl|bash.*",
    detectorcode literal
  • low Dangerous commands cmd-persistence integrated_rules/integrated_rules.json:1004
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    "raw_rule": "// YARA 规则：持久化攻击检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：systemd 服务、crontab、启动项、注册表后门\n\nrule Persistence_Systemd_Service {\n    meta:\n        description = \"检测 systemd 服务持久化\"\n        a
    detectorcode literal
  • low Secrets in code secret-high-entropy-token integrated_rules/integrated_rules.json:1015
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "YARA…ion",
    quoted
  • low Secrets in code secret-high-entropy-token integrated_rules/integrated_rules.json:1038
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "original_id": "YARA…ion",
    quoted
  • low Dangerous commands cmd-pipe-to-shell integrated_rules/integrated_rules.json:1117
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)
    "description": "检测 curl | bash 模式的远程代码执行",
    detectorcode literal
  • low Secrets in code secret-high-entropy-token integrated_rules/RULES_INDEX.yaml:329
    High-entropy token-like string (may be an id, hash or a credential)
    id: YARA…ion
  • low Instruction override en-ignore-previous INTEGRATION_REPORT.md:173
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition; documentation table row)
    | Prompt Injection | `ignore all previous instructions` | 检测到威胁 | ✅ 检测到 | PASS |
    detectortable
  • low Dangerous commands cmd-cron-mention QUICK_REFERENCE.md:113
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention README_SIGMA_YARA.md:278
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-background-process README_SIGMA_YARA.md:305
    Starts a background / autostarted process
    sudo systemctl enable defender-rules.service
  • low Secrets in code secret-high-entropy-token rules_backup/backup_20260407_195520/evasion_integrated.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "YARA…ion",
    quoted
  • low Secrets in code secret-high-entropy-token rules_backup/backup_20260407_195520/evasion_integrated.json:30
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "original_id": "YARA…ion",
    quoted
  • low Dangerous commands cmd-persistence rules_backup/backup_20260407_195520/persistence_integrated.json:29
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    "raw_rule": "// YARA 规则：持久化攻击检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：systemd 服务、crontab、启动项、注册表后门\n\nrule Persistence_Systemd_Service {\n    meta:\n        description = \"检测 systemd 服务持久化\"\n        a
    detectorcode literal
  • low Dangerous commands cmd-pipe-to-shell rules_backup/backup_20260407_195520/remote_load_integrated.json:12
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)
    "description": "检测 curl | bash 模式的远程代码执行",
    detectorcode literal
  • low Dangerous commands cmd-pipe-to-shell rules_backup/backup_20260407_195520/unknown_integrated.json:318
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)
    ".*curl|bash.*",
    detectorcode literal
  • low Secrets in code secret-high-entropy-token rules_backup/backup_20260407_195535/evasion_integrated.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "YARA…ion",
    quoted
  • low Secrets in code secret-high-entropy-token rules_backup/backup_20260407_195535/evasion_integrated.json:30
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "original_id": "YARA…ion",
    quoted
  • low Dangerous commands cmd-persistence rules_backup/backup_20260407_195535/persistence_integrated.json:29
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    "raw_rule": "// YARA 规则：持久化攻击检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：systemd 服务、crontab、启动项、注册表后门\n\nrule Persistence_Systemd_Service {\n    meta:\n        description = \"检测 systemd 服务持久化\"\n        a
    detectorcode literal
  • low Secrets in code secret-high-entropy-token rules/evasion_integrated.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "YARA…ion",
    quoted
  • low Secrets in code secret-high-entropy-token rules/evasion_integrated.json:30
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "original_id": "YARA…ion",
    quoted
  • low Dangerous commands cmd-persistence rules/persistence_integrated.json:29
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    "raw_rule": "// YARA 规则：持久化攻击检测\n// 版本：1.0\n// 日期：2026-03-21\n// 覆盖：systemd 服务、crontab、启动项、注册表后门\n\nrule Persistence_Systemd_Service {\n    meta:\n        description = \"检测 systemd 服务持久化\"\n        a
    detectorcode literal
  • low Dangerous commands cmd-pipe-to-shell rules/remote_load_integrated.json:12
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)
    "description": "检测 curl | bash 模式的远程代码执行",
    detectorcode literal

…and 1 more

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 38/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 146 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 84: 120–800 characters recommended
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 4 headings
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
The skill is a security scanner, but it also includes under-scoped autonomous research, rule-sync, backup/restore, and cross-project execution tools that users should review carefully before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026