ln-761-secret-scanner

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly directs the agent to fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched reference files (references/detection_patterns.md, references/remediation_guide.md) are read and used to drive scanning, classification, and remediation decisions—so external public GitHub content can materially influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly falls back to fetching runtime files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, which would inject external configuration/content used to control the scanner's behavior and prompts at runtime.