smugmug-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). This skill connects to and executes operations against the third‑party Smugmug service via the 'smugmug' toolkit (configured via RUBE_MANAGE_CONNECTIONS and invoked with RUBE_MULTI_EXECUTE_TOOL), which will ingest and require the agent to read user-generated content from a public third‑party site.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to the external MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS and RUBE_MULTI_EXECUTE_TOOL), which fetches tool schemas that drive agent instructions and invokes remote tool execution, so this URL directly controls prompts/execution.
Audit Metadata