BC qa-architecture-auditor
Perform forensic-level codebase analysis and generate comprehensive Quality Assurance and Testing Strategy Reports. Acts as Independent Principal QA Architect, Senior Software Security Auditor, and IT Systems Auditor. Uses zero-trust policy (ignores existing tests) and addresses all testing methodologies: Black Box, White Box, Manual, Automated, Unit, Integration, System, Functional, Smoke, Sanity, E2E, Regression, API, Database Integrity, Performance, Security, Usability, Compatibility, Accessibility, Localization, Acceptance, and Exploratory Testing. Use when needing a complete, independent testing strategy from scratch for any code repository.
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
AnalyzerSoftware developmentData and analyticstype and topics are labelled automatically from the skill text
How to improve
For the model run — optional
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
low Risky intent
intent-offensive-securityreferences/compliance-frameworks.md:26Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Security**: Security testing section covers OWASP Top 10, vulnerability scanning, penetration testing.
detector -
low Risky intent
intent-offensive-securityreferences/compliance-frameworks.md:43Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Incident Management**: Security testing includes vulnerability scanning and penetration testing.
detector -
low Risky intent
intent-offensive-securityreferences/methodologies.md:372Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Manual penetration testing at least annually or before major releases
-
low Risky intent
intent-offensive-securityreferences/methodologies.md:378Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Authorization Flaws**: Horizontal privilege escalation (User A access User B data); Vertical privilege escalation (user access admin functions)
-
low Risky intent
intent-offensive-securityreferences/methodologies.md:393Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Penetration Testing: Manual with Burp Suite, custom scripts
-
low Risky intent
intent-offensive-securityreferences/risk-assessment.md:200Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Critical**: Test exhaustively using all methodologies. Red team exercises. Penetration testing.
-
low Risky intent
intent-offensive-securityreferences/tooling-matrix.md:240Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| | **Burp Suite** | Professional penetration testing | Manual + automated |
-
low Risky intent
intent-offensive-securityreferences/tooling-matrix.md:298Offensive-security / dual-use content (legitimate for authorised testing; review intended use)17. **Penetration Testing**: Annual or release-based manual testing
-
low Risky intent
intent-offensive-securityself-audit.md:241Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)**Strategy:** Automated scanning, penetration testing, code reviews for OWASP Top 10, dependency vulnerability checks, and threat modeling.
detector
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 52/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, git, python) that frontmatter does not declare
- 100Steps. 40 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1529 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +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
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 654: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.
External checks
ClawHub: clean
This is a local codebase auditing skill with disclosed repository reads and local report writes, but its reports should be treated as advisory because its own sample output contains overconfident unsupported findings.
LLM: benign (medium) · VirusTotal: · 29 May 2026