product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes an 'auto-draft' feature that reads external codebase files (README, landing pages, marketing copy) to generate a context document, creating a surface for indirect prompt injection.
- Ingestion points: Codebase files including README, landing pages, and marketing materials.
- Boundary markers: No explicit delimiters are used for codebase data.
- Capability inventory: File system access to read repository contents and write to .agents/product-marketing-context.md.
- Sanitization: No sanitization of ingested file content is performed.
Audit Metadata