configure-skilllord

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly clones a public GitHub repository (Step 0: git clone https://github.com/affaan-m/claude-skill-lord.git) and then reads and acts on those third‑party SKILL.md and rule files (Steps 2–5 include copying, scanning, reading, and editing installed files), so untrusted repository content could influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs a runtime clone of the remote repository via "git clone https://github.com/affaan-m/claude-skill-lord.git /tmp/claude-skill-lord", and the fetched repo contains SKILL.md files, scripts, and hooks that are copied into the agent runtime and thus can directly control prompts or execute code, making this a required external dependency.