product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from the project's codebase (README, landing pages, marketing copy, etc.) to auto-draft documentation. Malicious instructions embedded in these files could potentially influence the agent's behavior during the drafting process.\n
- Ingestion points: Scans repository files such as README.md, package.json, and other marketing documents in the Step 2 workflow of SKILL.md.\n
- Boundary markers: None. The instructions do not define specific delimiters or include warnings to ignore instructions found within the source files.\n
- Capability inventory: The skill reads various codebase files and writes updates to .agents/product-marketing.md.\n
- Sanitization: No evidence of content validation or sanitization is present for the data fetched from the repository.\n- [COMMAND_EXECUTION]: The skill performs file system operations, including checking for file existence across multiple paths (.agents/, .claude/) and writing the context document to the project directory. These operations are required for its intended functionality.
Audit Metadata