x-post

Warn

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the xdk Python package. This package is not a commonly recognized or official SDK for the X/Twitter API, and it lacks version pinning, making it an unverifiable dependency from an unknown source.
  • [DATA_EXFILTRATION]: The script reads sensitive API credentials (API key, secrets, and access tokens) from a local JSON file (x.key). These credentials are then passed to the xdk library and sent over the network to X API endpoints. The use of an unverifiable third-party library to process these secrets represents a potential data exposure risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts text input that may be sourced from untrusted external data. Although the skill mandates a human-in-the-loop confirmation before posting, the capability to post to a public platform makes it a target for indirect injection attacks.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 1, 2026, 11:49 PM