travel-promos-argentina

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and parse promos from the public API at https://anduin.ferminrp.com/api/v1/promos (with data.source/permalink pointing to external origins), and the agent must read and apply that untrusted third‑party content to filter, rank, and decide which promotions to present.