product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from the repository (such as README.md, package.json, and marketing materials) to auto-draft a marketing context document, exposing an indirect prompt injection surface.
- Ingestion points: Scans local project files including README.md, package.json, and other repository documents during the auto-drafting process.
- Boundary markers: Absent. The instructions do not specify using delimiters or safety markers when reading and processing codebase content.
- Capability inventory: Performs file-read operations to gather information and file-write operations to create the .agents/product-marketing-context.md document.
- Sanitization: Absent. No filtering, validation, or sanitization of the content read from the repository is performed before the information is used to generate the draft.
Audit Metadata