The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external and user-provided data that could be used for indirect prompt injection attacks.
Ingestion points: The create_post and update_post tools ingest content (captions) and mediaUrls (external image/video links) into the workflow.
Boundary markers: The skill body lacks specific delimiters or instructions for the agent to treat the content and mediaUrls as data only and to ignore any embedded instructions.
Capability inventory: The skill allows the agent to make network requests to the Publora API (api.publora.com) and publish content to a linked TikTok account.
Sanitization: There is no evidence in the instructions of input validation or sanitization before processing the content through the tools.

tiktok-post