braintrust-tracing

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

• Third-party content exposure detected (high risk: 0.90). The skill queries the Braintrust service (e.g., via braintrust_analyze.py and the BRAINTRUST_API_URL https://api.braintrust.dev) and reads/replays session and Task span content (tool_input.prompt, tool_output, agent traces), which are user/agent-generated third-party data that the agent consumes as part of its workflow.