product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the codebase to generate marketing drafts.\n- Ingestion points: The skill reads repo files (README, package.json, marketing copy) in SKILL.md.\n- Boundary markers: Absent; no delimiters are used to wrap ingested content.\n- Capability inventory: The skill reads local files and writes to .claude/product-marketing-context.md.\n- Sanitization: Absent; the workflow relies on user review rather than automated sanitization.
Audit Metadata