onboard
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository, such as README files and AGENTS.md, which may contain instructions.
- Ingestion points: The agent reads project-specific documentation and configuration files including README.md, AGENTS.md, and .agents/ directories.
- Boundary markers: No explicit delimiters are used to separate external project instructions from the skill logic.
- Capability inventory: The skill is restricted to read-only operations, primarily directory listing and file reading; it does not have capabilities for network operations, file writing, or arbitrary command execution.
- Sanitization: No explicit filtering or sanitization of ingested content is performed.
- [SAFE]: No security issues detected. The skill performs standard repository orientation tasks using read-only operations and requires user confirmation for any proposed changes.
Audit Metadata