website-content-guide
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and logic are consistent with its stated purpose of generating content guides and branding documents. No patterns of prompt injection, data exfiltration, or obfuscation were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from
POSITIONING.md, which represents a potential attack surface for indirect prompt injection where instructions could be embedded in the positioning data. - Ingestion points: Reads positioning and audience information from
POSITIONING.mdin the local project directory. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content within the external document.
- Capability inventory: The skill writes to
CONTENT_GUIDE.mdandBRAND.md, and it can trigger command execution vianpm testfor tone validation. - Sanitization: The skill employs an automated tone test (
tone.spec.ts) to enforce stylistic constraints, providing a functional validation layer that limits the impact of certain prompt injection techniques.
Audit Metadata