linkedin-automation
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate instructions for LinkedIn automation through established tool sequences. No malicious commands or unauthorized data access patterns were found.
- [EXTERNAL_DOWNLOADS]: The skill references the external MCP server at https://rube.app/mcp. This is a known service for AI tool management and is documented as a safe configuration requirement.
- [PROMPT_INJECTION]: The skill handles user-provided text for posts and comments, which represents an indirect prompt injection surface. Ingestion points: user-supplied strings for LinkedIn posts and comments. Boundary markers: none provided. Capability inventory: network-based tool access to create LinkedIn content. Sanitization: none specified. This surface is intrinsic to the skill's purpose and does not impact the safety verdict.
Audit Metadata