twitter-automation

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to perform actions like posting tweets, sending DMs, and following users. These operations are conducted through the author's platform (inference.sh).
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and additional components hosted on the author's official GitHub repository (github.com/inference-sh/skills).
  • [INDIRECT_PROMPT_INJECTION]: The skill includes ingestion points for user-provided text (e.g., tweet content) which is then passed to the Twitter API. This is a standard functional requirement for social media automation skills.
  • Ingestion points: SKILL.md (input parameters for CLI commands)
  • Boundary markers: None
  • Capability inventory: Network operations via belt app run (SKILL.md)
  • Sanitization: None documented
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 01:28 AM
Security Audit — agent-trust-hub — twitter-automation