agent-trading-atlas

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly directs the agent to call the external ATA endpoints (e.g., "Query cohort evidence" with curl to "$ATA_BASE/api/v1/wisdom/query" and /api/v1/experiences) and read anonymized, user-submitted decision records and cohort summaries (user-generated third-party content) which the agent is expected to interpret and use to shape its analysis and submissions, creating a clear indirect prompt-injection surface.