gpc-app-recovery

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill analysis.
  • [COMMAND_EXECUTION]: The skill uses the gpc command-line tool to list, create, and manage app recovery actions, which aligns with its documented purpose.
  • [PROMPT_INJECTION]: The skill defines a surface for processing external data via JSON files. Evidence Chain: 1. Ingestion point: File system read of recovery.json and targeting.json in SKILL.md. 2. Boundary markers: Agent instructions require displaying the draft and obtaining user confirmation before deployment. 3. Capability inventory: Execution of gpc commands through a subprocess. 4. Sanitization: Not explicitly detailed, but the human-in-the-loop requirement provides a critical security checkpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:15 PM
Security Audit — agent-trust-hub — gpc-app-recovery