SKILLEMALL.ai
GitHub ↗ RU Sign in

BC skillguard

AI-powered security scanner for OpenClaw skills. Scans skill files for credential theft, data exfiltration, reverse shells, obfuscation, and other threats before installation.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files body ≈ 833 tokens Open the sourcegithub.com↗ analyzed 2 d ago

AI-powered security scanner for OpenClaw skills.

As a process C 57/100 · Has gaps — weak spots: when it triggers, failures and branches, consistency

ProcedureAI 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
B
75/100
safety, quality, tests
Safety 60%
75
Quality 40%
75
Run on models
none yet
Process rating
C
57/100
Has gaps
Failures and branches w 10
0
Progress reporting w 2
0
When it triggers w 12
20
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.

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 · 8

  • high Dangerous commands cmd-encoded-exec prompts/security-analysis.txt:17
    Executes a base64/encoded payload (documentation of a security skill)
    6. **Code Obfuscation**: base64 -d | bash, eval with dynamic content, hex-encoded shell commands, compressed payloads executed directly
    security skill
Medium and low: 7
  • low Dangerous commands cmd-privilege prompts/security-analysis.txt:13
    Privilege escalation / world-writable permissions (documentation of a security skill)
    4. **Privilege Escalation**: chmod u+s (setuid), sudo without user consent, writing to /etc/passwd, /etc/sudoers, cron with root
    security skill
  • low Risky intent intent-offensive-security prompts/security-analysis.txt:13
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    4. **Privilege Escalation**: chmod u+s (setuid), sudo without user consent, writing to /etc/passwd, /etc/sudoers, cron with root
  • low Dangerous commands cmd-privilege prompts/security-analysis.txt:29
    Privilege escalation / world-writable permissions (negated — the text forbids it)
    14. **Unusual Permissions**: chmod 777 on directories, removing execute permission from safety scripts
    negated
  • low Dangerous commands cmd-privilege README.md:68
    Privilege escalation / world-writable permissions (documentation of a security skill)
    | Privilege Escalation | sudo abuse, setuid, writing to `/etc/` |
    security skill
  • low Risky intent intent-offensive-security README.md:68
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Privilege Escalation | sudo abuse, setuid, writing to `/etc/` |
  • low Dangerous commands cmd-privilege SKILL.md:69
    Privilege escalation / world-writable permissions (documentation of a security skill)
    - **Privilege escalation**: sudo abuse, setuid bits, writing to `/etc/`
    security skill
  • low Risky intent intent-offensive-security SKILL.md:69
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Privilege escalation**: sudo abuse, setuid bits, writing to `/etc/`

Files scanned: 4. 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 57/100

  • 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
  • 40Consistency. Frontmatter name (skillguard) differs from the folder (farnwick-skillguard)
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 15 steps
  • 100Execution cost. Instruction body is 833 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 175: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 15 items
  • +3Output format is stated explicitly
  • +4Has examples (10 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.