NYC

gemini

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill executes a local Python script to interface with the Gemini CLI. This is the primary intended function and is performed using standard execution methods like uv run or python3.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it encourages passing untrusted data (e.g., file contents) directly into the prompt. Ingestion points: The prompt argument in the usage examples (e.g., $(cat app.py)). Boundary markers: No delimiters or instructions to ignore embedded commands are specified. Capability inventory: The script facilitates execution of local commands and communication with external AI services. Sanitization: No input sanitization or validation is mentioned in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:25 PM