The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint (https://rube.app/mcp) to provide the necessary tool suite for Instagram automation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from Instagram, which introduces a surface for indirect prompt injection via user-generated content.
Ingestion points: Untrusted data enters the agent context through tools like INSTAGRAM_GET_IG_MEDIA_COMMENTS and INSTAGRAM_GET_IG_MEDIA_CHILDREN, which retrieve public comments and media metadata.
Boundary markers: The skill does not define specific delimiters or instructions to treat retrieved comment data as untrusted text, potentially allowing embedded instructions to influence the agent.
Capability inventory: The skill has the ability to perform write operations, including creating posts (INSTAGRAM_CREATE_POST) and publishing media containers, which could be abused if an agent follows instructions found in comments.
Sanitization: No explicit sanitization, filtering, or validation logic is specified for the data retrieved from external Instagram tools.

instagram-automation