twitter-thread-creation

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the belt CLI tool and associated plugins via npx and links to official documentation on GitHub for setup. These references are standard for the tool's execution environment.
  • [COMMAND_EXECUTION]: Provides multiple examples of using the belt CLI (belt app run) to perform tasks like posting to Twitter, generating images from HTML, and using an agent-controlled browser. All commands are aligned with the skill's stated purpose of social media content creation.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents workflows for ingesting external data via search tools to generate content. While this represents a standard injection surface for LLMs, no malicious patterns were identified in the implementation instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — twitter-thread-creation