ln-627-observability-auditor

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch missing shared/reference files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} and marks several of those files as "MANDATORY READ" (e.g., audit_worker_core_contract.md, audit_scoring.md), meaning the agent will ingest and act on public GitHub content that could be user-controlled and thus could influence tool decisions and behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill states that if shared/ is missing it will fetch required runtime reference files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched "MANDATORY READ" contracts/templates directly control the worker's instructions/behavior, so this is a runtime external dependency that can alter prompts.