The Agent Skills Directory

[NO_CODE]: The skill consists entirely of API documentation and does not contain any executable scripts or binary files, which minimizes the risk of direct malicious action.
[INDIRECT_PROMPT_INJECTION]: The skill describes a system for processing external follower/following data from X/Twitter. This data represents an untrusted ingestion surface that could be used for indirect prompt injection. Ingestion points: Graph data retrieved via the specified API routes in SKILL.md. Boundary markers: No delimiters or safety instructions are defined in the provided usage examples. Capability inventory: The skill defines API interactions but includes no local execution capabilities. Sanitization: No sanitization or filtering of network data is described.

graph-analysis