skills/boshu2/agentops/ratchet/Gen Agent Trust Hub

ratchet

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the "ao" CLI and standard Unix utilities ("cat", "echo", "tail") to manage and report on the state of a development workflow. These commands are restricted to local operations within the project directory.
  • [PROMPT_INJECTION]: The skill reads workflow state from ".agents/ao/chain.jsonl", creating a potential surface for indirect prompt injection if the file content is externally influenced.
  • Ingestion points: ".agents/ao/chain.jsonl"
  • Boundary markers: Absent
  • Capability inventory: Local shell command execution ("ao", "cat", "echo")
  • Sanitization: Absent; relies on local file integrity
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 11:08 PM