gps-ops

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the gps CLI tool to interact with the Google Play Store API.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by providing tools to read user-generated content (app reviews).
  • Ingestion points: SKILL.md (via the gps_list_reviews and gps_search_review commands).
  • Boundary markers: None specified in the provided instructions.
  • Capability inventory: Local command execution via the gps CLI.
  • Sanitization: Not explicitly addressed.
  • [SAFE]: No high-severity security concerns such as base64 obfuscation, remote code execution from untrusted sources, or data exfiltration to unknown domains were found. The skill includes standard safety practices, such as requiring a confirmation flag for write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:45 PM
Security Audit — agent-trust-hub — gps-ops