alterlab-rma-citation-manager

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

• Third-party content exposure detected (high risk: 0.85). The skill's SKILL.md explicitly instructs the agent to "search the web for the latest edition specifics, publisher guidelines, and any recent updates" (Workflow step 1 / Agentic Protocol), meaning it will fetch and interpret open/public third‑party webpages whose content can change agent decisions and tool use.