instagram-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • External Dependency (LOW): The skill instructs the user to configure an MCP server using the URL https://rube.app/mcp. This is a third-party dependency outside the defined trusted organizations and repositories. While not an automated script execution, it introduces a reliance on an untrusted external service.
  • Indirect Prompt Injection (LOW): The skill includes functionality to retrieve external data that could contain malicious instructions.
  • Ingestion points: User comments retrieved via the INSTAGRAM_GET_IG_MEDIA_COMMENTS tool.
  • Boundary markers: None. The instructions do not provide delimiters or warnings to the agent to ignore instructions embedded within the retrieved comment text.
  • Capability inventory: The agent has the capability to create posts, publish media, and retrieve account insights across several scripts.
  • Sanitization: No sanitization or filtering of the comment content is mentioned or implemented in the workflow descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:18 AM