RobustaDev
Warn
Audited by Snyk on Feb 15, 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 supports loading external playbooks/actions from arbitrary repositories (e.g., the "playbookRepos" example with a GitHub URL in references/Actions.md) which the runner will fetch and execute, exposing the agent to untrusted third‑party content that could carry indirect prompt-injection payloads.
Audit Metadata