SKILLEMALL.ai
GitHub ↗ RU Sign in

CC Skill Flag Skill 🛡️

Scan Clawdbot/OpenClaw skills for malicious patterns, backdoors, and security risks.

modbender/skill-library-mcp Agent Skills author: modbender MIT 9 files body ≈ 750 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Scan Clawdbot/OpenClaw skills for malicious patterns, backdoors, and security risks.

As a process C 53/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency

ProcedureData and analyticstype 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
C
72/100
safety, quality, tests
Safety 60%
80
Quality 40%
60
Run on models
none yet
Process rating
C
53/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. 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 · 20

✓ No critical or high findings

Medium and low: 20
  • low Risky intent intent-offensive-security README.md:5
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Created by DarkM00n — Bug Bounty Hunter & Security Researcher.
  • low Risky intent intent-offensive-security README.md:96
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Bash reverse shell
  • low Risky intent intent-offensive-security README.md:141
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **DarkM00n** — Bug bounty hunter, Bitcoin security researcher, AI hacker.
  • low Dangerous commands cmd-pipe-to-shell-known-host reports/scan_20260130_2007.json:19
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed; documentation of a security skill)
    "content": "curl -LsSf https://astral.sh/uv/install.sh | sh"
    code literalsecurity skill
  • low Dangerous commands cmd-pipe-to-shell-known-host reports/scan_20260130_2007.json:28
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed; documentation of a security skill)
    "content": "curl -LsSf https://astral.sh/uv/install.sh | sh"
    code literalsecurity skill
  • low Exfiltration exfil-secret-in-url reports/scan_20260130_2007.json:298
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "content": "curl -s \"https://api.trello.com/1/members/me/boards?key=…&token=…" | jq '."
    placeholder
  • low Exfiltration exfil-secret-in-url reports/scan_20260130_2007.json:307
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "content": "curl -s \"https://api.trello.com/1/boards/{boardId}/lists?key=…&token=…" | "
    placeholder
  • low Exfiltration exfil-secret-in-url reports/scan_20260130_2007.json:316
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "content": "curl -s \"https://api.trello.com/1/lists/{listId}/cards?key=…&token=…" | jq"
    placeholder
  • low Exfiltration exfil-secret-in-url reports/scan_20260130_2007.json:325
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "content": "curl -s -X POST \"https://api.trello.com/1/cards?key=…&token=…" \\"
    placeholder
  • low Exfiltration exfil-secret-in-url reports/scan_20260130_2007.json:334
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "content": "curl -s -X PUT \"https://api.trello.com/1/cards/{cardId}?key=…&token=…" \\"
    placeholder
  • low Risky intent intent-offensive-security reports/template.md:78
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    This security scanner was created by DarkM00n, a bug bounty hunter and security researcher, to help the Clawdbot/OpenClaw community identify potentially malicious skills.
    detector
  • low Risky intent intent-offensive-security SKILL.md:11
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Created by:** DarkM00n (Bug Bounty Hunter & Security Researcher)

A further 8 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 9. 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 53/100

  • 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
  • 40Consistency. Frontmatter name (Skill Flag Skill 🛡️) differs from the folder (skill-flag)
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 19 steps
  • 100Execution cost. Instruction body is 750 tokens
  • 100Running it twice. Mutating operations check current state

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
  • -5TODO / placeholder text left in the skill
  • -214 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 19 items
  • +3Output format is stated explicitly
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.