connection-doctor

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is focused on diagnostic activities, using a set of read-only API tools (listAgents, getAgent, listConnections, etc.) to inventory and verify the health of agent connections.
  • [SAFE]: The instructions include a 'Safety floor' section which correctly identifies that external data such as connection names, error strings, and user-pasted transcripts must be treated as data only, effectively mitigating indirect prompt injection risks.
  • [SAFE]: The skill provides explicit instructions for handling sensitive information, directing the agent not to re-display detected credentials and to advise users on secret rotation if exposure occurs in logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:06 PM
Security Audit — agent-trust-hub — connection-doctor