The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection as it processes untrusted data from Instagram. • Ingestion points: The skill retrieves user-generated comments using the INSTAGRAM_GET_IG_MEDIA_COMMENTS tool. • Boundary markers: There are no instructions to use delimiters or ignore embedded commands within the processed data. • Capability inventory: The skill possesses significant capabilities, including the ability to publish posts and manage media containers. • Sanitization: No sanitization or validation of the retrieved comment data is described in the provided workflows.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to configure an external MCP server at https://rube.app/mcp. This third-party endpoint is required for the Instagram toolkit but involves sending data to a non-standard external service.
[NO_CODE]: No executable script files (.py, .js, .sh) are included in the skill; it consists purely of markdown-based tool usage instructions and configuration.

instagram-automation