SKILLEMALL.ai
GitHub ↗ RU Sign in

DD huo15-huo15-openclaw-enhance

火一五·克劳德·龙虾增强插件 v6.7.13 — large-file-bridge 兜底死循环修 + 用户上传后流程引导：实测用户『我已经上传好了』后 AI 没调 enhance_upload_check 反被兜底又塞了一份上传链接死循环。根因：before_agent_reply 每轮都触发,injectedSessions 有 entry + body 不含 URL → 强制 appendText 链接。修法：(1) entry 加 replyAppendUsed 标记,每次 inject 兜底只 fire 一次；(2) prompt 加『用户上传后处理流程』,明确 LLM 看到『传完了』必须 enhance_upload_check({token}) → Read → 处理任务,严禁再发链接 / 反问 / 全盘扫。Use when: 给 OpenClaw 加非侵入式增强（不改龙虾核心、不复制原生功能）。

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Job Zhao v6.7.21 MIT-0 74 files · 4 scripts body ≈ 2 833 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentsInfrastructuretype 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
D
53/100
safety, quality, tests
Safety 60%
44
Quality 40%
67
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ClawHub

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.

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.
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

  • high Dangerous commands cmd-persistence scripts/deploy-2week-followup-launchagent.sh:73
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST"
Medium and low: 14
  • medium Dangerous commands cmd-persistence scripts/deploy-2week-followup-launchagent.sh:8
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    # 里 launchctl load（红线 #5 诊断不修复 + #4 不 child_process）。
    comment
  • medium Dangerous commands cmd-persistence scripts/deploy-2week-followup-launchagent.sh:14
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    #   launchctl unload ~/Library/LaunchAgents/ai.h…ist
    comment
  • medium Dangerous commands cmd-persistence scripts/deploy-2week-followup-launchagent.sh:15
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    #   rm ~/Library/LaunchAgents/ai.h…ist
    comment
  • medium Dangerous commands cmd-persistence scripts/deploy-2week-followup-launchagent.sh:20
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST="$HOME/Library/LaunchAgents/${LABEL}.plist"
    code literal
  • medium Dangerous commands cmd-pipe-to-shell scripts/setup.sh:7
    Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)
    #   方式2: bash <(curl -fsSL https://raw.githubusercontent.com/jobzhao15/openclaw-enhance/main/scripts/setup.sh)
    comment
  • medium Dangerous commands cmd-persistence src/modules/trajectory-archiver.ts:197
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    `launchctl load "${path}"`,
    code literal
  • low Secrets in code secret-high-entropy-token package-lock.json:147
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…wIN//F77/IADDSs58i+MDaO…jeo+YFg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:269
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…wrY+hNh3PljmZ+37oA…yhQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:496
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…RAu+EGHG…L8i+zXBl…44B/Kom4…sXQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:716
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…0fQ+SO3G…qRw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:821
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Qa1+6LtJ…AZZ+7JPP…MTQ==",
    detector
  • low Dangerous commands cmd-persistence scripts/audit-session-bridge-and-share-fallback.sh:255
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation of a security skill)
    launchctl unload "\$HOME/Library/LaunchAgents/ai.h…ist"
    code literalsecurity skill
  • low Dangerous commands cmd-persistence scripts/audit-session-bridge-and-share-fallback.sh:256
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation of a security skill)
    rm "\$HOME/Library/LaunchAgents/ai.h…ist"
    code literalsecurity skill
  • low Dangerous commands cmd-shell-rc scripts/postinstall.cjs:70
    Writes to a shell startup file (string literal in code, not executed)
    "       " + c.dim + "echo 'export BOT_BASE_URL=https://your-domain.com' >> ~/.zshrc" + c.reset + "\n" +
    code literal

Files scanned: 74. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 41/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (huo15-huo15-openclaw-enhance) differs from the folder (huo15-openclaw-enhance)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 73 steps
  • 100Execution cost. Instruction body is 2833 tokens
  • 100Progress reporting. Reports progress
  • low 15 top-level sections: this looks like several domains in one skill

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)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -2localhost URLs: will not work for another user
  • -215 emoji in the instructions: noise for the model
  • -44 reference files, but SKILL.md never points to them: the model will not open them
  • -34 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 411: enough signal without eating the budget
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 73 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: suspicious
This appears to be a real OpenClaw enhancement plugin, but it enables a broad set of memory, file sharing, prompt-hook, local scanning, and task-dispatch behaviors that are not fully reflected in the narrow top-level description.
LLM: suspicious (high) · VirusTotal: · 25 Jun 2026