The Agent Skills Directory

[SAFE]: The skill operates entirely on local repository documentation and configuration files to synthesize index files for AI agents. It does not perform network operations or access sensitive credentials.
[COMMAND_EXECUTION]: The skill references standard development tools such as pnpm, vitest, and eslint within its documentation templates, which is expected for its purpose.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from repository files like README.md and package.json. While this is an ingestion surface, the output is restricted to a static documentation file, and the risk of automated instruction following from malicious repository content is considered low and inherent to agentic development tools.

agents-md