ripgrep
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the
rg(ripgrep) utility. It specifically recommends security mitigations such as using literal mode (-F) for user-supplied strings and proper single-quoting to prevent shell expansion of special characters like!,$, and backslashes. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to search and ingest content from local repository files and logs into the agent's context, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: File content and log data returned by
rg(SKILL.md). - Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions found within search results.
- Capability inventory: The skill enables the
rgtool which can read any file visible to the agent's environment. - Sanitization: While command-line arguments are sanitized for shell safety, the resulting data stream from the files themselves is treated as raw input without specific prompt injection filtering.
Audit Metadata