ln-001-push-all

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

• Third-party content exposure detected (high risk: 0.90). The SKILL mandates loading reference files from shared/references and, if missing, explicitly fetches them via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, so it will ingest public GitHub raw content (untrusted, user-controlled) that can materially influence linting, commit, and push behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs that if shared/ is missing it must fetch files at runtime via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} and mandates reading shared reference files (e.g., git_scope_detection.md and ci_tool_detection.md), so remote content fetched from that URL would directly control agent instructions and is a required runtime dependency.