product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Susceptibility to indirect prompt injection through repository analysis.
- Ingestion points: Reads README, landing pages, marketing copy, and package.json from the codebase (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the ingestion logic.
- Capability inventory: Reads repository files and writes a marketing context document to .claude/product-marketing-context.md, which is designed to be referenced by subsequent marketing tasks.
- Sanitization: No automated sanitization is performed on the ingested content, though the workflow includes a user review step.
Audit Metadata