gemini
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
geminiCLI for analysis tasks and utilizes system tools such asps,lsof,kill, andpkillto manage potentially hung background processes. - [DATA_EXFILTRATION]: The skill transmits workspace context, including code and architectural plans, to the external Gemini API via the CLI for its intended analysis functionality.
- [PROMPT_INJECTION]: The skill processes untrusted workspace data, creating a surface for potential indirect prompt injection.
- Ingestion points: Code and plan analysis tasks ingest content from the user's local workspace.
- Boundary markers: The skill does not use explicit delimiters or instructions to ignore embedded commands within the processed files.
- Capability inventory: The skill utilizes the
geminiCLI and standard system process management commands. - Sanitization: There is no evidence of explicit input sanitization or validation performed on the workspace data before analysis.
Audit Metadata