asana

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md requires the agent to call Apideck's proxy endpoint (https://unify.apideck.com/proxy) to fetch raw responses from the Asana API (https://developers.asana.com/docs), which will deliver user-generated/untrusted Asana content (tasks, comments, etc.) that the agent is expected to read and could materially influence subsequent actions.