product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill automates the drafting of marketing context by ingesting untrusted content from the repository. * Ingestion points: README, landing pages, marketing copy, and package.json are read from the codebase to generate drafts. * Boundary markers: The instructions lack specific delimiters or instructions for the agent to ignore embedded commands within the ingested files. * Capability inventory: The agent can read project files and write the resulting marketing context to .agents/product-marketing.md. * Sanitization: No explicit sanitization or filtering logic is defined for the external content before it is processed by the model.
Audit Metadata