ln-523-auto-test-planner

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly falls back to fetching "shared/" reference files from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} and marks several of those files (e.g., shared/references/risk_based_testing_guide.md, research_tool_fallback.md, environment_state_contract.md) as "MANDATORY READ" that the agent must parse and use to drive planning and delegation, so it ingests untrusted public GitHub-hosted content that can materially influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly falls back to fetching mandatory reference files at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched docs/templates are required and used to control the agent's planning/instruction logic.