missive-automation
Warn
Audited by Snyk on Feb 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to call RUBE_SEARCH_TOOLS against Rube MCP (https://rube.app/mcp) to fetch live tool schemas, tool slugs, and recommended execution plans which are third-party content the agent must read and act on, exposing it to untrusted external input.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill requires using the external Rube MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS / RUBE_MULTI_EXECUTE_TOOL), which invokes remote Composio tools and thus can execute remote code on which the agent's actions depend.
Audit Metadata