instagram-automation
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to add an external endpoint (
https://rube.app/mcp) as an MCP server. This server provides the tool implementations for the Instagram automation. Users should ensure they trust the provider of this endpoint as it defines the actions the agent can perform. - [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing external data (captions and media URLs) from potentially untrusted sources.
- Ingestion points:
caption,image_url, andvideo_urlparameters in theINSTAGRAM_CREATE_MEDIA_CONTAINERandINSTAGRAM_CREATE_CAROUSEL_CONTAINERtools. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided for the input parameters.
- Capability inventory: The skill provides extensive tools for publishing content and retrieving account-level insights from Instagram.
- Sanitization: The documentation does not specify any sanitization, validation, or filtering of the content before it is processed by the tools.
- [SAFE]: The documented workflows for media creation, container polling, and two-phase publishing are consistent with the official Instagram Graph API requirements for Business and Creator accounts.
Audit Metadata