product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core functionality of reading and processing local repository data.
- Ingestion points: Scans codebase files such as README, package.json, and landing pages to automatically draft marketing context.
- Boundary markers: The instructions lack explicit delimiters or directions for the agent to ignore instructions that might be embedded within the source files.
- Capability inventory: The agent has permissions to read local files and write to the
.agents/product-marketing.mddocument. - Sanitization: No specific sanitization, validation, or filtering of the ingested content is performed prior to using it for document generation.
Audit Metadata