adrapid-automation
Warn
Audited by Snyk on Feb 16, 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 the agent to call RUBE_SEARCH_TOOLS and related RUBE_* APIs against the public Rube/Composio endpoints (e.g., https://rube.app/mcp and composio.dev) to fetch tool schemas, auth links, and execution plans which the agent must read and act on, exposing it to untrusted third‑party content that could carry indirect prompt injections.
Audit Metadata