The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the infsh CLI for application execution, including content research and media generation. The execution environment is restricted by the allowed-tools configuration, which limits shell access to only the vendor's specific command line tool.
[EXTERNAL_DOWNLOADS]: References installation documentation and additional skill modules from the vendor's official GitHub repository (inference-sh). These resources are documented as part of the intended setup process for the vendor's ecosystem.
[PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface as it ingests data from external search providers and uses it to drive downstream actions like social media posting.
Ingestion points: Output from external search queries via tavily/search-assistant (SKILL.md).
Boundary markers: No explicit delimiters or boundary markers are defined in the command examples.
Capability inventory: The skill can invoke applications for image generation and social media posting (x/post-create, html-to-image) (SKILL.md).
Sanitization: No explicit validation or filtering of external search results is described.

linkedin-content