NYC

debugger

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Data Exposure (LOW): The skill suggests commands like 'env | grep -i debug'. While standard for troubleshooting, this can expose sensitive environment variables if they contain the keyword 'debug'.
  • External Downloads (LOW): The README contains a link to an untrusted GitHub repository ('Charon-Fan/agent-playbook'). While the link is informational, the repository is not on the trusted sources list.
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted data (error messages and logs). This represents a surface for indirect prompt injection, though the impact is limited to the agent's existing bash and file-write capabilities used for debugging tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:09 PM