The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes two Python scripts, risk-prioritize.py and check-ac-testability.py, which are used for local data processing. risk-prioritize.py computes risk scores from JSON input, and check-ac-testability.py uses regular expressions to analyze markdown text for testability. Both scripts use standard Python libraries and do not perform network operations or access sensitive system files.
[DYNAMIC_EXECUTION]: The skill includes a test suite (tests/) that uses subprocess.run to execute the local Python scripts via the current Python interpreter. This is a standard and safe practice for verifying the functionality of command-line utilities within a development or testing environment.
[EXTERNAL_DOWNLOADS]: The reference documentation contains links to well-known technology services and research organizations, such as Anthropic, Playwright, Vercel, Arxiv, and the official homepages for testing tools like PIT, Stryker, and Mutmut. These links are provided for instructional and documentation purposes and do not involve the execution of remote code.
[INDIRECT_PROMPT_INJECTION]: The skill features a vulnerability surface where it ingests untrusted user data (markdown specifications and JSON risk items) for analysis. However, the associated scripts have no capabilities for network exfiltration, file system writes, or command execution based on that input. risk-prioritize.py additionally includes input validation for data types and numeric ranges, mitigating basic schema confusion risks.

qa-methodology