The Agent Skills Directory

[External Reference] (LOW): The skill instructs users to connect to an external MCP server at https://rube.app/mcp. This domain is not listed as a trusted source. Although integral to the skill, users should verify the security of third-party MCP providers.
[Indirect Prompt Injection] (LOW): The skill is vulnerable to indirect prompt injection as it retrieves content from external users. 1. Ingestion points: INSTAGRAM_GET_IG_MEDIA_COMMENTS tool output. 2. Boundary markers: Absent; no specific delimiters or instructions are provided to the agent to distinguish data from instructions. 3. Capability inventory: The skill possesses write capabilities such as INSTAGRAM_CREATE_POST. 4. Sanitization: Absent; no sanitization of retrieved comment text is implemented.

instagram-automation