tools-code-search

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as fd, rg, git grep, and git log. These commands are used for their intended purpose of discovering and reading codebase artifacts to support architecture reviews and system mapping.- [PROMPT_INJECTION]: The skill processes untrusted content from the local codebase, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Content is ingested from local files through search results generated by rg, fd, and git ls-files.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent incorporates these search results into its context.
  • Capability inventory: The agent possesses file-writing and command-execution capabilities, which could be targeted by instructions embedded in the code it searches.
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the content discovered during searches before further processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 10:31 AM
Security Audit — agent-trust-hub — tools-code-search