The Agent Skills Directory

[SAFE]: The skill primarily focuses on job search automation and data processing. All core logic is implemented in local scripts (e.g., build_search_queries.py, dedupe_postings.py, score_posting.py) that use the Python standard library. These scripts do not perform unexpected network requests, credential harvesting, or unauthorized file access.\n- [COMMAND_EXECUTION]: Static analysis identified the use of subprocess.run() in tests/test_score_posting.py. This is part of the test suite and is used exclusively to verify the command-line interface of the scoring script by executing the local script with the current Python interpreter. This is standard testing behavior and does not represent a security risk.\n- [SAFE]: The skill processes job postings fetched from external websites. While this involves handling untrusted data, the skill mitigates risk by extracting specific fields and applying a structured scoring rubric. The results are formatted as user-facing HTML and JSON files within the workspace, which is consistent with its intended purpose.

job-search