adaptyv

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls the public Adaptyv Foundry API (foundry-api-public.adaptyvbio.com) in SKILL.md and references/api-endpoints.md (e.g., GET /results, GET /sequences, GET /targets, GET /updates, POST /targets/request-custom and webhook handling), which returns user-supplied/untrusted sequences, results, notes and updates that the agent is expected to read and act on (create/submit experiments, follow status/webhook-driven flows), so third-party content could materially influence agent behavior.