The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script (scripts/review.py) designed to perform static analysis on TypeScript files using regular expressions. The script is restricted to reading file contents and does not execute any code, perform network operations, or utilize dangerous functions like eval() or os.system().
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized data exfiltration patterns were detected. Code snippets using fetch or JSON.parse are provided strictly as educational examples and are not executed by the skill's infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code as its primary function. While this presents an ingestion surface for untrusted data, the instructions provide a highly specific and constrained rubric (the 62 items from Effective TypeScript) for the agent to follow, which effectively mitigates the risk of the agent obeying malicious instructions embedded in code comments.

effective-typescript