The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the orth command-line utility to perform API requests to the Fiber AI service. This includes searching for profiles, companies, and jobs, as well as validating email addresses. All commands are structured calls to the vendor's own API.
[PROMPT_INJECTION]: The skill ingests external, potentially untrusted data from LinkedIn, including profile details, posts, comments, and reactions. This constitutes an indirect prompt injection surface where malicious content within processed LinkedIn data could attempt to influence agent behavior.
Ingestion points: Data retrieved from LinkedIn via endpoints such as /v1/linkedin-live-fetch/profile-posts and /v1/linkedin-live-fetch/post-comments in SKILL.md.
Boundary markers: The skill does not define specific boundary markers or instructions to treat the external content as untrusted.
Capability inventory: The skill's capabilities are focused on data retrieval and search via the orth tool; it does not request broader system access like file system modification or arbitrary shell execution.
Sanitization: No explicit sanitization or filtering of the content fetched from LinkedIn is documented in the skill instructions.

fiber