The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external code and configuration files, which could contain malicious comments or data designed to influence the agent's analysis or summary.
Ingestion points: Source code files identified in Step 1 and analyzed in Steps 3-6, including architecture, tests, documentation, and infrastructure configuration files.
Boundary markers: Absent. The skill does not define specific delimiters or "ignore" instructions for the content being read.
Capability inventory: File system discovery (find), file reading (grep), shell command execution (git, go, pytest, npx, gh), and report generation (TECH_DEBT.md).
Sanitization: Absent. There is no evidence of filtering or sanitizing the input from the analyzed files before processing.
[COMMAND_EXECUTION]: The skill executes standard development and analysis tools locally to gather metrics.
Fetches repository configuration and branch protection status using the GitHub CLI (gh api).
Executes project-specific testing and coverage tools including go test, pytest, and jest via npx.
Performs repository history analysis using git commands.

tech-debt