product-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase to generate documentation, creating a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read various files including README, package.json, landing pages, and marketing copy in SKILL.md (Step 2: Gather Information).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the processed files are defined.
- Capability inventory: The skill possesses file-read capabilities across the repository and file-write capabilities specifically to create .agents/product-marketing.md.
- Sanitization: No evidence of sanitization, filtering, or validation of the content read from external files before interpolation into the agent's context.
Audit Metadata