twitter-automation

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill facilitates interaction with the inference.sh platform using its official CLI tool, belt.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation guides from inference.sh and its official GitHub repository. These are recognized as legitimate resources for the service's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-generated content for social media posting, which presents a standard ingestion surface.
  • Ingestion points: Untrusted data enters the agent context via the --input argument in Bash commands defined in SKILL.md.
  • Boundary markers: The skill uses structured JSON payloads to encapsulate user data, providing a clear boundary between instructions and data.
  • Capability inventory: The skill uses the Bash(belt *) tool to execute CLI commands for posting tweets, sending DMs, and managing user profiles.
  • Sanitization: Data is passed as structured JSON to the CLI, minimizing the risk of command injection within the shell environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 10:59 PM
Security Audit — agent-trust-hub — twitter-automation