pexels-automation
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill requires the configuration of an external MCP server at
https://rube.app/mcp. This domain is not included in the list of trusted GitHub organizations or verified providers, posing a supply-chain risk where the remote server could be altered without notice. - REMOTE_CODE_EXECUTION (MEDIUM): Through tools like
RUBE_REMOTE_WORKBENCHandRUBE_MULTI_EXECUTE_TOOL, the agent executes operations orchestrated by the remote server. If the server is compromised, it could provide malicious execution plans to the agent. - DYNAMIC_EXECUTION (MEDIUM): The instructions mandate calling
RUBE_SEARCH_TOOLSto fetch schemas and execution plans at runtime. This creates a pattern where the agent's operational logic is entirely determined by untrusted remote data rather than static, reviewed code. - INDIRECT_PROMPT_INJECTION (LOW): The skill ingests data from Pexels (external API results). While a standard function, this constitutes an attack surface for indirect prompt injection if the ingested content (e.g., image metadata) contains malicious instructions.
Audit Metadata