braintrust-map-eval-evidence

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). In SKILL.md + references/interaction-contract.md, the workflow explicitly performs trace/dataset-driven auditing (e.g., “Inspect before asking” and “Trace content is evidence”), meaning outsider-authored text can be ingested via user/system-under-test outputs present in traces or dataset rows.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 20, 2026, 10:16 PM
Issues
1