# Security Linter

> Scans agent bootstrap files and skills for known prompt-injection phrasing and reports matches for human review.

- Skill: `gl0di/security-linter` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add gl0di/security-linter`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gl0di/security-linter/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: gl0di (https://skillmd.com/u/gl0di)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/gl0di/security-linter

---


# Security Linter

A small, defensive utility skill. It never executes anything it finds — it only
greps for known attack phrasing (the same class of phrase ClawSecCheck itself
detects) and reports matches so a maintainer can review them by hand.

See `linter.py` for the phrase catalogue and `cleanup.sh` for the temp-file
housekeeping this skill runs between scans.