imgbb-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill requires the user to add a non-whitelisted external MCP server (
https://rube.app/mcp) to their configuration. This creates a functional dependency on an external third-party service provider. - PROMPT_INJECTION (LOW): Indirect Prompt Injection vulnerability surface (Category 8). The instructions direct the agent to fetch and follow "recommended execution plans" and "tool schemas" from the remote
RUBE_SEARCH_TOOLSendpoint. - Ingestion points: Data returned from the
RUBE_SEARCH_TOOLScommand inSKILL.md. - Boundary markers: Absent. The skill lacks instructions to delimit or ignore instructions embedded within the search results.
- Capability inventory: The skill has the capability to execute tools via
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCH. - Sanitization: Absent. There is no mention of validating or sanitizing the input schemas or plans provided by the remote server.
- COMMAND_EXECUTION (LOW): The skill facilitates the execution of remote tools through
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCH. Since this is the primary intended purpose of the skill, the severity is low, but it remains a notable capability surface.
Audit Metadata