context-fetch
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions and examples for using command-line search utilities such as ripgrep (rg), grep, and PowerShell's Select-String to find patterns in the codebase.
- [PROMPT_INJECTION]: The skill is designed to search and read contents from the project's source directory, which constitutes a surface for indirect prompt injection. Ingestion points: Local filesystem (src/ directory) via search and read commands. Boundary markers: No specific boundary markers or instructions to ignore embedded content are included. Capability inventory: Use of shell commands (rg, grep, Get-Content) and the view_code_item tool. Sanitization: No sanitization of ingested content is performed.
Audit Metadata