SKILLEMALL.ai
GitHub ↗ RU Sign in

FD Cue - 你的专属调研助理 / Your AI Research Assistant

统一入口和智能路由中心，自动识别用户意图并路由到相应技能。基于 Cue 产品设计，提供专业化的深度研究体验。

Blockedguard blocked the skill: signs of malicious behaviour
modbender/skill-library-mcp Agent Skills author: modbender MIT 52 files · 12 scripts body ≈ 2 879 tokens Open the sourcegithub.com↗ analyzed 3 d ago

统一入口和智能路由中心，自动识别用户意图并路由到相应技能。基于 Cue 产品设计，提供专业化的深度研究体验。

As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructureSoftware developmenttype 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
25/100
safety, quality, tests
Safety 60%
0
Quality 40%
62
Run on models
none yet
Process rating
D
44/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

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.

Secrets in code
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 If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail.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.

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.

Dangerous commands 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 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.

How to improve

  1. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  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 · 15

  • critical Secrets in code secret-openai-key backups/scripts-v1.0.3-20260226-015020/cue.sh:287
    OpenAI-style API key (quoted — discussed, not commanded)
    echo "   sk-s…l3k"
    quoted
  • critical Secrets in code secret-openai-key REVISION_REPORT.md:116
    OpenAI-style API key
    sk-s…l3k
Medium and low: 13
  • medium Exfiltration net-redirectable-api-key backups/scripts-v1.0.3-20260226-015020/cuecue-client.js:307
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Dangerous commands cmd-persistence SECURITY_FIX_v1.0.4.md:118
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    (crontab -l 2>/dev/null | grep -v "$SCRIPT_DIR"; echo "$cron_cmd") | crontab -
    security skill
  • low Secrets in code secret-high-entropy-token backups/scripts-v1.0.3-20260226-015020/cue.sh:287
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    echo "   sk-s…l3k"
    quoted
  • low Dangerous commands cmd-background-process COMPARISON_v1.0.4_vs_v1.0.3.md:128
    Starts a background / autostarted process
    nohup bash -c "..." &
  • low Secrets in code secret-high-entropy-token package-lock.json:293
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…ywo+qwL+oL8H…C1U+vRfLQDvw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:309
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha512-Yqfm+XDx0+Prh3…1yC+JWZ2…IL7+vK+Clp7…D7g==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:322
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…xZl+RoGR…fbT/ZgrF…0EA==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:335
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…3bJ+V0If…IXN+CL65…a4w==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:351
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…H47+FFon…OsV/4+RRsz…0ig==",
    quoted
  • low Secrets in code secret-high-entropy-token REVISION_REPORT.md:116
    High-entropy token-like string (may be an id, hash or a credential)
    sk-s…l3k
  • low Dangerous commands cmd-cron-mention SECURITY_FIX_v1.0.4.md:118
    Mentions editing / listing crontab (documentation of a security skill)
    (crontab -l 2>/dev/null | grep -v "$SCRIPT_DIR"; echo "$cron_cmd") | crontab -
    security skill
  • low Dangerous commands cmd-cron-mention SECURITY_FIX_v1.0.4.md:169
    Mentions editing / listing crontab (code comment; documentation of a security skill)
    // 使用用户级 cron (crontab -e) 而非系统级
    commentsecurity skill
  • low Dangerous commands cmd-cron-mention TEST_REPORT_v1.0.3.md:161
    Mentions editing / listing crontab (test fixture / example file)
    if crontab -l 2>/dev/null | grep -q "monitor-daemon"; then
    fixture

Files scanned: 52. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 44/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 7 mutating operations with no state check
  • 40Consistency. Frontmatter name (Cue - 你的专属调研助理 / Your AI Research Assistant) differs from the folder (cue)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 94 steps
  • 100Execution cost. Instruction body is 2879 tokens

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 54: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -244 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 94 items
  • +4Has examples (14 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.