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