ably-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 / RUBE_GET_TOOL_SCHEMAS (via the Rube MCP endpoint https://rube.app/mcp and composio.dev toolkits) to fetch third-party tool slugs, input schemas and recommended execution plans that the agent is expected to read and act on, exposing it to untrusted external content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires adding and connecting to the Rube MCP endpoint (https://rube.app/mcp) at runtime to fetch tool schemas and "recommended execution plans" via RUBE_SEARCH_TOOLS, which directly control agent instructions and execution and is a required dependency.
Audit Metadata