runhuman-testing
Warn
Audited by Snyk on Mar 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill instructs agents to create tests against arbitrary URLs and to "wait" for and "view detailed results" from Runhuman (see SKILL.md "Wait for Results" /
runhuman results <jobId>), which means the agent will ingest untrusted, user-generated human tester feedback from a third-party service that can materially influence subsequent actions.
Audit Metadata