twitter-automation

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the belt CLI and other related skills from the belt-sh and inference-sh ecosystems. It also references official documentation hosted on inference.sh and github.com.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run the belt CLI for performing actions like posting tweets, following users, and sending direct messages. This is the core intended functionality of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles user-provided data, such as tweet content and usernames, which is passed as input to the CLI tool. This represents the standard operational flow for this type of automation skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:21 PM
Security Audit — agent-trust-hub — twitter-automation