soleur-skill-security-scan git:20261007.8bcbe03A

Immutable. This exact content never changes and is served at /api/v1/blob/7b8dffdf176bfcb5.

---
name: soleur-skill-security-scan
description: "This skill should be used when scanning Claude Code skills or agent files for advisory security risks: code-execution, prompt-injection, supply-chain, filesystem-boundary, telemetry. Emits LOW-RISK | REVIEW | HIGH-RISK."
---

On Cursor, do not call the Skill tool, the Task tool, `run_subagent`, or AwaitShell, and do not expand `CLAUDE_PLUGIN_ROOT`. If the canonical file tells you to call those tools, stop. Slice 1 does not run hooks, does not classify the session as cursor, and does not block a commit.

Read `skills/skill-security-scan/SKILL.md`, relative to the plugin root.