quality-auditor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill's primary function is to ingest and analyze untrusted external data (code and documentation), which provides a surface for embedded instructions to influence the agent.
- Ingestion points: Processes content from 'DOCS/', 'README.md', 'CLI/', and 'SKILLS/' directories.
- Boundary markers: None identified in the manifest or usage guide to isolate untrusted content from the agent's instructions.
- Capability inventory: The manifest declares capabilities to 'modifies_files' and 'creates_artifacts', and the documentation mentions testing the 'bootstrap process', implying potential code execution.
- Sanitization: No evidence of sanitization or validation of audited content is present in the skill files.
- No Code (SAFE): The provided files consist of markdown documentation and a manifest; no executable scripts (e.g., Python, JavaScript) were detected.
Audit Metadata