product-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate project management tasks by creating and updating a markdown file (.agents/product-marketing.md) to store product positioning and audience information.
- [INDIRECT_PROMPT_INJECTION]: The skill's 'auto-draft' feature creates an entry point for indirect prompt injection by reading repository content (README, landing pages, package.json) to generate marketing drafts.
- Ingestion points: Step 2 in SKILL.md reads various files from the codebase to extract marketing information.
- Boundary markers: No specific delimiters or safety instructions are used when processing codebase content.
- Capability inventory: The skill uses file-write operations to save the document to .agents/product-marketing.md in SKILL.md.
- Sanitization: The skill relies on human review and confirmation before final document creation, which serves as a primary control against malicious content from the codebase.
Audit Metadata