product-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The 'Auto-draft from codebase' feature automatically reads various files within the user's repository, including READMEs, marketing copy, and documentation, to generate the product marketing context document.
- Ingestion points: The skill ingests data from local repository files such as README.md, package.json, landing page files, and general documentation files.
- Boundary markers: No specific boundary markers, delimiters, or 'ignore' instructions are defined to encapsulate the ingested content.
- Capability inventory: The skill is capable of reading repository files and writing a shared context file to .agents/product-marketing.md.
- Sanitization: There is no evidence of sanitization or validation performed on the content read from the repository.
- Downstream Impact: The resulting context file is explicitly designed to be a shared reference for other marketing skills (copywriting, ads, social, etc.), creating a potential multi-step injection chain where malicious content in a single repository file could influence multiple downstream agent operations. The skill includes a user review step as a mitigation factor.
Audit Metadata