omh-agent-board

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied coordination requests. * Ingestion points: User requests and target context are ingested into the workflow (SKILL.md). * Boundary markers: The skill explicitly defines 'not-evidence boundaries' and 'prepared-vs-observed' boundaries to separate instructions from execution proof. * Capability inventory: Uses the omh_agent_board tool and omh CLI. * Sanitization: Includes instructions to report missing authority or observed evidence rather than blindly following instructions.
  • [COMMAND_EXECUTION]: The skill uses a platform-specific CLI tool to track runtime status. * Evidence: omh runtime record --skill agent-board --harness agent-board --status started.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:33 PM
Security Audit — agent-trust-hub — omh-agent-board