gemini
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
geminiCLI tool for performing AI-based tasks like Q&A and text generation. - [INDIRECT_PROMPT_INJECTION]: The skill processes natural language prompts through a command-line interface, which is susceptible to indirect prompt injection if the inputs contain malicious instructions.
- Ingestion points: The positional prompt argument passed to the
geminicommand as documented inSKILL.md. - Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the prompt input.
- Capability inventory: Executes the
geminiCLI which performs network requests to Google's API and returns generated content to the agent. - Sanitization: No input validation or sanitization of the prompt strings is specified in the skill instructions.
Audit Metadata