ask-navigator
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
node scripts/shipyard-audit.mjsto perform repository audits.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external issue trackers (GitHub, GitLab), creating a vulnerability surface for indirect prompt injection.\n - Ingestion points: External issue tracker bodies and comments.\n
- Boundary markers: Absent.\n
- Capability inventory: File system writes to
.omc/,docs/, andCONTEXT.md, tracker API interaction, and background subagent spawning.\n - Sanitization: Absent.
Audit Metadata