The Agent Skills Directory

[SAFE]: The skill operates as described, performing local codebase analysis without signs of malicious intent.- [EXTERNAL_DOWNLOADS]: Fetches the skill definition from the author's own GitHub repository during installation.- [COMMAND_EXECUTION]: Uses the Bash tool to navigate the project filesystem and manage report directories, which is expected for this utility.- [PROMPT_INJECTION]: The skill's design involves processing untrusted codebase content with high-capability tools (Bash, Write), presenting a potential surface for indirect prompt injection.
Ingestion points: Codebase files and directory structures at the specified analysis path.
Boundary markers: Prompts for sub-agents do not include specific delimiters or instructions to ignore embedded directives within the files being analyzed.
Capability inventory: Read, Write, Glob, Grep, Bash, and Task (for sub-agent orchestration).
Sanitization: No sanitization of code comments or documentation content is performed before synthesis.

analyze-codebase