twitter-automation

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches setup guidelines from the official inference-sh GitHub repository (raw.githubusercontent.com/inference-sh/skills/...).
  • [COMMAND_EXECUTION]: Uses the 'belt' utility for social media automation. The execution environment restricts available commands to this specific utility via the allowed-tools configuration.
  • [PROMPT_INJECTION]: The skill accesses external user-generated content from Twitter/X (e.g., via 'x/post-get' or 'x/user-get'), which represents a surface for indirect prompt injection. Boundary markers and sanitization are not explicitly defined in the tool wrappers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:03 PM