data-refresh-eval
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly builds datasets by fetching customer conversations from Front (see the dataset build commands and required FRONT_API_TOKEN in SKILL.md/.env.local), ingesting untrusted user-generated messages that the agent reads and uses to run routing/evaluation workflows, so third-party content could indirectly inject instructions.
Audit Metadata