file-search
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the
fdandripgreputilities for searching the file system. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes the contents of local files which may contain malicious instructions meant to influence the agent.
- Ingestion points: File content retrieved through the
ripgrep (rg)tool (SKILL.md). - Boundary markers: The skill lacks instructions for the agent to use delimiters or ignore potential commands within the searched file content.
- Capability inventory: The skill enables subprocess execution of
fdandrgwhich interact directly with the file system (SKILL.md). - Sanitization: No validation or sanitization of search results is defined to prevent the processing of untrusted data.
Audit Metadata