product-marketing
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration behaviors were detected. The skill operates within the scope of its stated documentation and intended purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading repository content to auto-draft documentation. This is a core intended functionality.
- Ingestion points: Local codebase files including README.md, landing pages, marketing copy, and package.json as defined in SKILL.md.
- Boundary markers: Not present; the skill lacks specific markers to delimit or ignore instructions within ingested files.
- Capability inventory: File system read access to the project repository and write access to the .agents/ directory.
- Sanitization: The workflow incorporates a mandatory user review and manual correction phase before the final document is saved, which serves as a mitigation for potentially malicious instructions embedded in source files.
Audit Metadata