ln-636-manual-test-auditor

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs (top of SKILL.md) that if shared/ is missing it must "fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}" and also lists multiple "MANDATORY READ" shared/references files that the agent must load and interpret as part of its workflow, so untrusted public GitHub content could materially influence behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs that if shared/ is missing it will WebFetch runtime files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those mandatory "MANDATORY READ" reference/template files directly control the worker's instructions/behavior, so this is a runtime external dependency that can change prompts.