product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files (README, package.json, landing pages) which could potentially contain malicious instructions if the repository content is untrusted.
- Ingestion points: Reading local files including
README,package.json, and marketing copy files in the codebase (SKILL.md). - Boundary markers: The instructions do not explicitly tell the agent to ignore or delimit instructions found within the analyzed files.
- Capability inventory: The skill has filesystem read/write access to manage the
.claude/product-marketing-context.mdfile, but lacks network or command execution capabilities. - Sanitization: No explicit sanitization or filtering of ingested file content is performed before presentation to the LLM.
Audit Metadata