product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted project data, creating a surface for indirect prompt injection.
- Ingestion points: Reads repository files including README, landing pages, marketing copy, and package.json.
- Boundary markers: Absent; the skill lacks instructions to delimit or ignore instructions embedded in source files.
- Capability inventory: Executes file system reads and writes to .claude/product-marketing-context.md.
- Sanitization: Absent; the skill does not sanitize or validate ingested content.
- [NO_CODE]: The skill is composed of markdown instructions without any executable code or scripts, which limits the attack surface to the agent's interaction with repository data.
Audit Metadata