The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from LinkedIn (profile and company information) while possessing write capabilities (posting, commenting), which creates a surface for indirect prompt injection.
Ingestion points: Data is ingested from LinkedIn via LINKEDIN_GET_MY_INFO and LINKEDIN_GET_COMPANY_INFO as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to the agent to disregard embedded commands in the retrieved data.
Capability inventory: The agent is granted capabilities to create posts, manage images, comment, and delete posts.
Sanitization: No sanitization or validation logic is specified for the data retrieved from external sources before it is processed.
[EXTERNAL_DOWNLOADS]: The skill configuration points to an external MCP server at https://rube.app/mcp to provide its core functionality.

linkedin-automation