AC skill-scanner
Security-first skill vetting for AI agents on OpenClaw and Claude Code. Scans any SKILL.md for malicious patterns, permission abuse, prompt injection, and ClawHavoc attack vectors — then gives a clear Safe / Caution / Danger verdict. Use this skill whenever the user wants to install, review, vet, or audit a skill from ClawHub, GitHub, or any other source; asks "is this skill safe?", "should I install this?", "scan/check/vet this skill", "review skill before installing"; shares a SKILL.md file or skill URL; or pastes skill content for evaluation. Proactively offer to scan any skill the user mentions installing, even if they don't explicitly ask for a security check.
As a process C 62/100 · Has gaps — weak spots: result and completion, consistency, progress reporting
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 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
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Risky intent
intent-offensive-securitySKILL.md:52Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Credential harvesting:**
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (skill-scanner) differs from the folder (skill-scanner-v1)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 1871 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 673: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.