codebase-exploration
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions and examples for executing shell-based search and analysis tools, including
rg(ripgrep),fd,ast-grep,git log, andtree. These commands are used to identify patterns, file structures, and code history within a local repository. - [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted codebase data during search tasks.
- Ingestion points: Content is ingested from any file within the search scope of the codebase.
- Boundary markers: The instructions do not implement delimiters or safety instructions to prevent the agent from obeying instructions embedded in the searched code.
- Capability inventory: The skill leverages tools with file-read and repository-metadata capabilities (
rg,fd,git,ast-grep). - Sanitization: No content validation or sanitization is performed on the data retrieved from the codebase prior to analysis.
Audit Metadata