The Agent Skills Directory

[SAFE]: The skill provides a legitimate technical guide for X API integration, promoting the use of established libraries over manual implementations to ensure security and consensus compatibility on the Internet Computer.
[CREDENTIALS_UNSAFE]: The instructions correctly differentiate between public identifiers (Client ID) and sensitive tokens, providing guidance on secure OAuth 2.0 PKCE implementation without hardcoding any secrets.
[REMOTE_CODE_EXECUTION]: The skill references the x-client Motoko package via the mops package manager. This is a standard dependency management practice in the Motoko ecosystem and does not involve untrusted or obfuscated remote execution.
[INDIRECT_PROMPT_INJECTION]: The provided code handles external input (body and accessToken) to perform network operations. While this defines an ingestion surface for social media posting, it is the primary intended function of the skill and follows standard development patterns.

connector-x