AC skulk-skill-scanner
Scan OpenClaw skill folders for security red flags before installing or publishing. Detects data exfiltration, credential theft, prompt injection, destructive commands, obfuscation, privilege escalation, and supply chain risks. Use when: evaluating a skill from ClawHub before install, auditing your own skills before publishing, or reviewing any SKILL.md for safety. NOT for: general code review or vulnerability scanning of non-skill codebases.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-privilegescripts/scanner.js:140Privilege escalation / world-writable permissions (documentation of a security skill)/(?:chmod\s+[+u]s|setuid|setgid)/gi,
security skill -
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)description: "Scan OpenClaw skill folders for security red flags before installing or publishing. Detects data exfiltration, credential theft, prompt injection, destructive commands, obfuscation, priv
detector -
low Risky intent
intent-offensive-securitySKILL.md:41Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| 🟠 High | Obfuscation (base64/eval), unknown network access, env scanning, privilege escalation, hidden instructions |
detector
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 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
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 511 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 446: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.