omh-triage-driver

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Phase 3 instructions guide the agent to perform repository actions such as closing or updating issues using shell commands. It recommends a specific shell-loop idiom with temporary files in /tmp to ensure reliable execution of multi-line data. This behavior is standard for the skill's intended purpose as a development and maintenance tool.
  • [PROMPT_INJECTION]: The skill processes untrusted data from repository issue backlogs, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: Issue counts, label distributions, repository metadata, and migration history (Phase 0).
  • Boundary markers: No specific delimiters or "ignore instructions" warnings for external issue content are explicitly defined in the instructions.
  • Capability inventory: The skill utilizes the terminal toolset for executing repository updates and board modifications (Phase 3).
  • Sanitization: No automated sanitization or filtering logic is mentioned; however, the workflow includes an explicit user-gate/review checkpoint before any execution occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 09:18 AM
Security Audit — agent-trust-hub — omh-triage-driver