facebook-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server at https://rube.app/mcp. This third-party endpoint provides the tools and logic necessary for the Facebook integration.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it interacts with data from an external social media platform.
  • Ingestion points: The agent reads data from Facebook comments, posts, insights, and page descriptions via the Rube MCP toolkit.
  • Boundary markers: There are no boundary markers or instructions to help the agent distinguish between legitimate data and potential instructions embedded within Facebook content.
  • Capability inventory: The skill allows for high-impact actions including creating/editing/deleting posts, replying to comments, and managing ad accounts.
  • Sanitization: The skill does not define any sanitization, filtering, or validation logic for the content retrieved from the Facebook API.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:35 PM