braintrust-plan-agent-eval
Warn
Audited by Snyk on Aug 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill “braintrust-plan-agent-eval” takes free-form user requests as input (broad eval/planning prompts) and uses that text to restate the product decision and determine the next lifecycle stage, so an outsider can supply arbitrary instructions via the user request that the runtime LLM ingests directly.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata