The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to bypass safety filters, extract system prompts, or override agent behavior.- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access (like SSH keys), or network calls to external domains were detected.- [Obfuscation] (SAFE): The file consists of clear text markdown with no Base64, zero-width characters, or encoded commands.- [Unverifiable Dependencies & RCE] (SAFE): The skill does not perform any package installations or remote script executions. It references standard Python tools (ruff, mypy, black) as recommendations for developers rather than runtime dependencies.- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze external Python code and configuration files. While this is an inherent attack surface for indirect injection via code comments or docstrings, the skill provides a strict structured template for responses which helps mitigate the risk of the agent obeying embedded commands.

python-reviewer