product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs standard file-based documentation tasks within the project repository. It does not utilize network operations or external script execution.
- [DATA_EXFILTRATION]: The skill reads project-level files such as README and package.json to extract marketing information. This behavior is restricted to the local workspace and does not target sensitive paths (like SSH keys or credentials) or transmit data externally.
- [COMMAND_EXECUTION]: The skill does not contain any commands for shell execution, subprocess spawning, or system-level modifications; it relies on the agent's native file-handling capabilities.
- [PROMPT_INJECTION]: The skill has an ingestion surface as it reads data from the codebase to generate content. Ingestion points: README, landing pages, marketing copy, about pages, package.json. Boundary markers: None present. Capability inventory: File reading and File writing. Sanitization: None specified.
Audit Metadata