twitter-automation

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and CLI documentation from the inference-sh GitHub organization (e.g., https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). These references are consistent with the skill's primary purpose of providing an integration for the inference.sh platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied text for social media posts and direct messages.
  • Ingestion points: Input JSON payloads for belt app run commands in SKILL.md.
  • Boundary markers: User-provided content is wrapped within structured JSON objects passed as command arguments.
  • Capability inventory: The skill is restricted to the belt CLI tool via the allowed-tools configuration in the frontmatter, limiting the impact of potential injections to social media operations.
  • Sanitization: The skill relies on the inference.sh platform's internal handling and Twitter's API constraints for content sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — twitter-automation