oc-subagent

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes shell scripts like sanity.sh to perform static analysis on persona configurations and verify platform status.
  • [EXTERNAL_DOWNLOADS]: The fetcher persona is explicitly designed to retrieve external content from URLs using provided retrieval tools as part of its document ingestion role.
  • [REMOTE_CODE_EXECUTION]: Specialized personas such as coder and theorem-prover include capabilities to execute and compile code (e.g., Lean4) as part of their intended domain functionality.
  • [SAFE]: The architecture implements strong security practices, including automated checks for prompt leakage and structured communication protocols using auditable receipts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:00 PM
Security Audit — agent-trust-hub — oc-subagent