ocrspace-automation
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill directs the user to add an external MCP server endpoint (
https://rube.app/mcp). While typical for MCP integrations, this is a dependency on a non-trusted third-party source. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill explicitly instructs the agent to follow "recommended execution plans" and "pitfalls" returned dynamically from a remote search tool (
RUBE_SEARCH_TOOLS). - Ingestion points: Data and instructions returned by the
RUBE_SEARCH_TOOLSquery at runtime. - Boundary markers: Absent. The instructions do not provide delimiters or warnings to treat the search results as untrusted input.
- Capability inventory: High-impact capabilities including
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCHwhich can execute various automation tools. - Sanitization: Absent. There is no logic provided to validate the integrity or safety of the execution plans retrieved from the remote server.
Audit Metadata