Skills
Navigate
skills/peachest/skills/pi-events-doctor/Gen Agent Trust Hub

pi-events-doctor

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands to gather diagnostic evidence.
  • Evidence: Uses sqlite3 to query the daemon's persistence layer in references/checks.md.
  • Evidence: Uses journalctl --user -u pi-events-daemon to audit service logs for timeouts and errors.
  • Evidence: Uses grep and wc to analyze patterns within session logs.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to processing untrusted data from previous agent sessions.
  • Ingestion points: The skill reads session transcripts from ~/.pi/agent/sessions/**/*.jsonl as part of the diagnostic process (referenced in SKILL.md and references/checks.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the session files are defined.
  • Capability inventory: The skill can read local files, execute SQL queries, and write diagnostic summaries to the ~/ops directory.
  • Sanitization: No sanitization or filtering of the content within the .jsonl files is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 10:43 AM