The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard command-line tools for static analysis and repository diagnostics.
Evidence: usage of git log, git diff, cloc, and radon within code-health.md for analyzing code frequency and complexity.
[EXTERNAL_DOWNLOADS]: The skill references established package managers and security auditing tools which are common in development workflows.
Evidence: execution of npm audit and pip-audit for dependency checking, and npx eslint for linting in code-health.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from git logs and tool outputs which could theoretically contain malicious content, but it does so within a limited capability context.
Ingestion points: git log output, linter reports, and audit logs.
Boundary markers: Not explicitly defined in the provided snippets.
Capability inventory: Limited to Read, Grep, and Glob tools.
Sanitization: No explicit sanitization of tool output before display, however, this is standard for diagnostic tools.

quality