AB security-auditor
Perform comprehensive security audits on codebases, infrastructure configs, API designs, and architecture documents. Use this skill whenever the user wants to review code or config for vulnerabilities, assess security posture, identify attack surface, produce a findings report, or get remediation recommendations. Trigger on phrases like "security review", "audit this", "find vulnerabilities", "is this secure", "pen test", "threat model", "OWASP", "check for CVEs", "security assessment", or any request to assess risk in code, infra, or system design — even if the word "audit" isn't used. Covers web apps, APIs, cloud configs, IAM policies, secrets management, auth flows, and more.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:109Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **High** | Significant risk requiring exploitation of one step; privilege escalation, SQLi, SSRF |
-
low Risky intent
intent-offensive-securitySKILL.md:152Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation paths
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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (security-auditor) differs from the folder (security-auditor-x)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 6 branches
- 85Steps. 49 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 1635 tokens
- 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 687: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 49 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.