gemini-qa

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill recommends installing the Gemini CLI via npm or from GitHub. The repository 'google-gemini/gemini-cli' is a specifically trusted source according to the analysis guidelines, which results in a SAFE status for this reference.
  • [COMMAND_EXECUTION] (SAFE): The skill uses shell commands to invoke the 'gemini' executable. This is the intended primary function of the skill and does not appear to involve arbitrary or malicious command construction.
  • [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8).
  • Ingestion points: Local files and directory contents referenced via the '@' syntax or piped via 'cat' (as described in SKILL.md).
  • Boundary markers: Absent; the content is passed directly as context to the CLI tool without explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill allows reading any file in the workspace and executing the 'gemini' command with that content.
  • Sanitization: None detected; the skill passes raw file content to the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM