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 runcommands inSKILL.md. - Boundary markers: User-provided content is wrapped within structured JSON objects passed as command arguments.
- Capability inventory: The skill is restricted to the
beltCLI tool via theallowed-toolsconfiguration 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