debug-my-harness

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and interprets data from an external file (.vigiles/runs.jsonl) to diagnose system behavior.
  • Ingestion points: Reads records from the .vigiles/runs.jsonl log file.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to ignore potentially malicious instructions embedded within the JSONL records.
  • Capability inventory: The skill is limited to reading the file and providing analysis; it does not perform writes, network requests, or command execution.
  • Sanitization: There is no evidence of sanitization or validation of the JSON records before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 01:16 AM
Security Audit — agent-trust-hub — debug-my-harness