The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script (scripts/bilibili.py). This is the primary method of operation and is constrained to the skill's own distributed code. The script includes a gated execution model requiring an explicit --confirm flag for any state-changing actions (publishing or deleting drafts).
[DATA_EXPOSURE]: The skill manages sensitive authentication data via the BILIBILI_COOKIES environment variable. The instructions and the script contain explicit warnings and logic to prevent echoing or printing these secrets to the output or logs.
[REMOTE_CODE_EXECUTION]: An SSRF (Server-Side Request Forgery) protection mechanism is implemented in the image rehosting logic. The _assert_public_url function prevents the script from accessing private, loopback, or link-local IP addresses when fetching images for rehosting on Bilibili's CDN. It also blocks redirects to prevent bypassing these checks.
[SAFE]: Connections to api.bilibili.com are official API endpoints for the service the skill is designed to interact with. The reference to auth.acedata.cloud for connection management belongs to the vendor's infrastructure as defined in the author context.

bilibili