ai-readability-audit
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to audit external websites, which introduces a surface for indirect prompt injection where malicious instructions could be hidden in the analyzed site's metadata or content.
- Ingestion points: External website content, structured data, and Meta information (SKILL.md).
- Boundary markers: Not specified in the provided manifest files.
- Capability inventory: Implied network read capability to retrieve website data for auditing.
- Sanitization: No sanitization or filtering logic is visible in the provided metadata.
- [No Executable Code] (SAFE): The analyzed files consist solely of Markdown documentation and YAML metadata. No scripts, binaries, or active code components were provided for analysis.
Audit Metadata