AB repo-security-auditor
Audit GitHub repositories for security vulnerabilities, malicious code patterns, and suspicious behavior. Clone repos, analyze code for backdoors, data exfiltration, obfuscation, dependency risks, and license compliance. Generate a security report and optionally scaffold a clean reimplementation if the repo passes safety checks. Use when: user wants to "review a GitHub repo for security", "check if code is safe", "audit repository for malicious code", "analyze repo before using", "scan dependencies", "recreate this repo safely", or any request involving security analysis of third-party code. Do NOT use for: repos you own and trust, general code review without security focus, or when user only wants a feature summary without security checks.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 5. 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 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 85Steps. 24 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2398 tokens
- 100Running it twice. Mutating operations check current state
- low 12 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
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 750: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 24 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.