Skills
skills/backnotprop/pstack/automate-me/Gen Agent Trust Hub

automate-me

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git log to query file history for mining scope.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted conversation history. Ingestion points: agent-transcripts/ directory. Boundary markers: Absent. Capability inventory: create-skill (file-write) and Git. Sanitization: None.
  • [SAFE]: No obfuscation, data exfiltration, or malicious persistence mechanisms were found. The skill includes explicit instructions to respect workspace boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 05:53 PM
Security Audit — agent-trust-hub — automate-me