skills/xexr/marketplace/doctor-triage/Gen Agent Trust Hub

doctor-triage

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local command-line tools gt and bd with various subcommands and flags (e.g., doctor, --fix, q, update) to diagnose and resolve workspace issues. These operations are restricted to the local environment and align with the tool's intended administrative functions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from diagnostic tools to categorize and act upon workspace errors.
  • Ingestion points: Output from gt doctor -v and bd doctor -v is parsed to triage issues.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate tool output from agent instructions.
  • Capability inventory: The agent can execute fix commands, restart sessions, and create new issue records (beads) using bd q.
  • Sanitization: No explicit sanitization of tool output is performed before interpretation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 10:40 AM