The Agent Skills Directory

[SAFE]: The skill's primary function is to assist in code search and navigation using legitimate command-line utilities without exhibiting malicious behaviors or obfuscation.
[COMMAND_EXECUTION]: The skill uses the Bash tool to run search and version control commands.
Evidence: It includes instructions for executing grep to find patterns and git commands (blame, log) to trace code history, which are standard for codebase navigation.
[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to read and interpret content from external codebase files.
Ingestion points: Data is ingested from the local filesystem via the Read, Grep, and Glob tools.
Capability inventory: The agent can execute shell commands through the Bash tool based on its findings.
Boundary markers: The instructions do not define clear delimiters to separate file content from instructions.
Sanitization: The skill does not implement specific filtering or validation of the content read from files.
[NO_CODE]: The skill consists solely of instructions and metadata without including any scripts or executable files.

codebase-search