twitter-automation
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill facilitates interaction with the inference.sh platform using its official CLI tool,
belt. - [EXTERNAL_DOWNLOADS]: The skill references documentation and installation guides from inference.sh and its official GitHub repository. These are recognized as legitimate resources for the service's functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-generated content for social media posting, which presents a standard ingestion surface.
- Ingestion points: Untrusted data enters the agent context via the
--inputargument in Bash commands defined inSKILL.md. - Boundary markers: The skill uses structured JSON payloads to encapsulate user data, providing a clear boundary between instructions and data.
- Capability inventory: The skill uses the
Bash(belt *)tool to execute CLI commands for posting tweets, sending DMs, and managing user profiles. - Sanitization: Data is passed as structured JSON to the CLI, minimizing the risk of command injection within the shell environment.
Audit Metadata