gps-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill details the use of the gps command-line interface for tasks like identity verification (gps whoami) and command discovery (gps ops).- [PROMPT_INJECTION]: The discovery commands take user-supplied keywords (e.g., gps search <keyword>), establishing an ingestion point for external data that could be used for indirect prompt injection. 1. Ingestion points: User-provided keywords in discovery commands in SKILL.md. 2. Boundary markers: The skill does not include specific delimiters or instructions to ignore embedded commands in the keyword input. 3. Capability inventory: The skill uses shell execution capabilities for the gps utility. 4. Sanitization: There are no instructions for validating or escaping the user-provided search terms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:45 PM
Security Audit — agent-trust-hub — gps-troubleshooting