parma-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: 0.90). The skill instructs the agent to query the external Rube MCP endpoint (https://rube.app/mcp) via RUBE_SEARCH_TOOLS and ingest returned tool slugs, input schemas, and recommended execution plans from that public third-party source (and linked composio.dev docs), which the agent is expected to read and could contain untrusted/user-provided instructions.
Audit Metadata