gps-ops

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by instructing the agent to interpolate user-provided data directly into shell command templates.
  • Ingestion points: Untrusted data enters the context through the $PKG environment variable and JSON argument strings used in the gps call examples within SKILL.md.
  • Boundary markers: There are no boundary markers or explicit instructions provided to the agent to validate or sanitize these inputs to prevent command injection or instruction override.
  • Capability inventory: The gps CLI tool provides capabilities to read from and write to the Google Play Store (e.g., listing reviews, managing tracks, and replying to reviews).
  • Sanitization: No sanitization, escaping, or schema validation logic is defined for the external content before it is processed by the CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 03:34 PM
Security Audit — agent-trust-hub — gps-ops