The Agent Skills Directory

[SAFE]: The skill is purely instructional and documentation-based, providing setup guides for the official Python security tool Bandit.
[EXTERNAL_DOWNLOADS]: The skill references and downloads dependencies from well-known and trusted sources, including the official Python Package Index (PyPI) and official GitHub repositories.
Evidence: pip install bandit[toml] (official PyPI package).
Evidence: repo: https://github.com/PyCQA/bandit (official repository for the Bandit tool).
[COMMAND_EXECUTION]: The skill provides standard command-line examples for running Bandit, which is the primary purpose of the skill. These commands are safe and align with the tool's intended use.
Evidence: bandit -r . and --severity-level flags are standard operational parameters.
[PROMPT_INJECTION]: No prompt injection patterns or attempts to override agent behavior were detected in the instructions or metadata.
[DATA_EXFILTRATION]: No network operations to unknown domains or sensitive file access patterns were identified. The network references are limited to trusted documentation sites and package registries.

bandit-python