The Agent Skills Directory

[SAFE]: The skill and the sloplint.js utility perform intended text analysis and formatting tasks. No malicious patterns, data exfiltration, or unauthorized credential access were identified.
[COMMAND_EXECUTION]: The skill includes a zero-dependency Node.js CLI tool (sloplint.js) and an installer script (scripts/install-git-hook.sh). These tools execute local commands for filesystem traversal, Git status checks, and Git hook installation. These actions are transparent, documented, and aligned with the tool's purpose as a development utility.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external text and repository files. To mitigate risks associated with untrusted data, the instructions include a strict 'no-fabrication' rule and a multi-step verification process (draft, audit, final) to maintain fidelity to the original source.
[PERSISTENCE]: The skill provides a script to install a Git pre-commit hook. While this creates a persistent execution point in the local development environment, it is a standard industry practice for linters and is explicitly initiated by the user or agent during setup.

humanize