content-quality-auditor
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from external URLs using the WebFetch tool, which creates a surface for indirect prompt injection where malicious instructions embedded in the audited content could attempt to manipulate the audit results or influence agent behavior.
- Ingestion point: Content is retrieved from user-provided URLs via the WebFetch tool.
- Boundary markers: The skill includes a dedicated 'Security boundary' section in SKILL.md that explicitly warns the agent to treat fetched content as data, not instructions, and to ignore directives targeting the audit process.
- Capability inventory: The skill writes audit artifacts to the memory/ directory and updates state files such as memory/hot-cache.md and memory/open-loops.md.
- Sanitization: No technical sanitization of HTML is performed; the skill relies on instructional guardrails to ensure the agent maintains the correct context during the audit.
Audit Metadata