The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, specifically the TikTok API (profile information, statistics, and video lists).
Ingestion points: Data is received via TikTok API scopes such as user.info.basic, user.info.stats, and video.list as described in SKILL.md.
Boundary markers: The skill implements a provenance system (user_confirmed, platform_verified, genfeed_observed) to categorize data and prevent context confusion.
Capability inventory: No dangerous capabilities like subprocess execution or file system modification are utilized in the provided scripts.
Sanitization: The skill provides advisory output formats and explicitly instructs the agent to avoid automated actions or making unsupported claims about platform algorithms.

tiktok-warmup