product-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing 'skene-skills' from the vendor's GitHub repository. This is a legitimate extension of the vendor's own functionality.
- [COMMAND_EXECUTION]: The agent is instructed to search the user's codebase for specific strings like 'onboarding' and libraries such as 'intro.js' to help diagnose the current state.
- [INDIRECT_PROMPT_INJECTION]: The skill's codebase audit feature processes untrusted local files, creating a potential surface for indirect prompt injection. The agent should treat content from these files as data rather than instructions.
- Ingestion points: Codebase files searched during the audit phase (SKILL.md).
- Boundary markers: None explicitly defined.
- Capability inventory: File reading and searching capabilities.
- Sanitization: No specific sanitization of file content is described.
Audit Metadata