AD skill-audit
Security scanner for OpenClaw skills. Analyzes skill folders and .skill files for: prompt injection, data exfiltration, malicious scripts, suspicious network connections, dangerous code patterns, and unauthorized access. Use when: (1) BEFORE installing any skill from ClawHub or the internet — always scan first, (2) auditing an already-installed skill, (3) reviewing a skill's security posture, (4) checking what APIs/MCPs/env vars a skill uses, or (5) the user asks 'is this skill safe?'. IMPORTANT: This skill acts as a pre-install security hook. When the clawhub skill is used to install a new skill, ALWAYS run skill-audit on the installed skill BEFORE confirming success to the user.
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 3. 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 44/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-audit) differs from the folder (openclaw-skill-audit)
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 24 steps
- 100Execution cost. Instruction body is 715 tokens
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- -212 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 689: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (4 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.