The Agent Skills Directory

[SAFE]: No malicious behavior or security risks were identified. The skill correctly implements tools for its stated purpose of repository search and navigation.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to read and process content from external repositories. This risk is inherent to any tool that analyzes third-party data and is mitigated here by the skill's discovery-oriented workflow. Ingestion points: files processed by the Read and Grep tools. Boundary markers: No specific delimiters or safety instructions are defined for the agent when presenting file content. Capability inventory: The skill has access to Bash, Read, Grep, and Glob tools. Sanitization: No explicit content validation or filtering is performed on the files being searched.

codebase-search