product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from the local codebase to draft marketing documentation, creating a surface for indirect prompt injection. * Ingestion points: Reads files including README, landing pages, marketing copy, about pages, and package.json. * Boundary markers: No explicit markers or delimiters are used to separate ingested file content from the agent's internal instructions. * Capability inventory: Involves local file read operations and writing to the .claude/ directory. * Sanitization: Ingested content is not sanitized or validated for embedded commands before being processed by the agent.
- [NO_CODE]: This skill consists of markdown instructions without any accompanying executable scripts or binaries.
Audit Metadata