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 references and fetches installation instructions from the official inference-sh repository on GitHub.- [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to perform various automated tasks on Twitter/X, such as posting tweets, liking content, and following users.- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes user-defined text to be posted to social media platforms.
  • Ingestion points: User-provided strings for tweet text and direct messages found in the Bash examples in SKILL.md.
  • Boundary markers: None present; the skill uses standard JSON input formats without specific injection-prevention delimiters.
  • Capability inventory: The skill has the capability to perform network operations (posting to Twitter) and send messages via the inference.sh infrastructure.
  • Sanitization: There is no evidence of explicit content sanitization within the skill's instructions, relying on the underlying platform's handling of the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:21 PM
Security Audit — agent-trust-hub — twitter-automation