AC secure-code-guardian
Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security implementations such as hashing passwords with bcrypt/argon2, sanitizing SQL queries with parameterized statements, configuring CORS/CSP headers, validating input with Zod, and setting up JWT tokens. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention, secure session management, and security hardening. For pre-built OAuth/SSO integrations or standalone security audits, consider a more specialized skill.
Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security…
As a process C 64/100 · Has gaps — weak spots: when it triggers, failures and branches
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:32Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Authorization**: Verify horizontal and vertical privilege escalation paths are blocked; test with tokens belonging to different roles/users.
-
low Risky intent
intent-offensive-securitySKILL.md:56Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Log security events (failed auth, privilege escalation attempts)
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 48): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 64/100
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1536 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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)
- +2Single-language instructions
- +3Description length 594: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.