wrike-automation
Warn
Audited by Snyk on Jun 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required runtime workflow uses Composio’s Wrike MCP tools (e.g.,
WRIKE_FETCH_ALL_TASKS,WRIKE_GET_TASK_BY_ID,WRIKE_GET_FOLDERS) to ingest Wrike task/folder content into the agent context; that content is authored by Wrike users other than the operating user (outsider-authored free text like task titles/descriptions/comments), creating an indirect prompt-injection path.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). This skill requires contacting the external MCP server https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas and connection info that directly determine available prompts and executable tool behaviors, making it a required runtime dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata