BC skill-security-auditor
Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.
Command-line security analyzer for ClawHub skills.
As a process C 60/100 · Has gaps — weak spots: when it triggers, failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Exfiltration
intent-browser-credential-storepatterns/malicious-patterns.json:86Accesses a browser credential / cookie store (detector / deny-list definition)"pattern": "Cookies|Login Data|Web Data|chrome/Default|firefox/profiles",
detector -
medium Risky intent
intent-wallet-secretsSKILL.md:176Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Wallet private key patterns
-
low Dangerous commands
cmd-shell-rcREADME.md:163Writes to a shell startup file (documentation of a security skill)echo 'alias audit-skill="~/.openclaw/skills/skill-security-auditor/analyze-skill.sh"' >> ~/.bashrc
security skill -
low Risky intent
intent-offensive-securityREADME.md:187Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Credential Harvesting** - API keys, SSH keys, wallet access
-
low Risky intent
intent-offensive-securitySKILL.md:62Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Credential harvesting patterns
-
low Dangerous commands
cmd-shell-rcSKILL.md:112Writes to a shell startup file (documentation of a security skill)echo 'alias audit-skill="~/.openclaw/skills/skill-security-auditor/analyze-skill.sh"' >> ~/.bashrc
security skill -
low Risky intent
intent-offensive-securitySKILL.md:173Offensive-security / dual-use content (legitimate for authorised testing; review intended use)3. **Credential Harvesting**
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "emoji"
Process rating: all ten parameters 60/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 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. 129 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3419 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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)
- -227 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 246: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 129 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.