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 refers to official installation scripts and documentation from the inference-sh organization on GitHub. These downloads are legitimate resources provided by the service vendor.
- [COMMAND_EXECUTION]: The skill uses the
beltCLI to execute Twitter actions. The tool usage is constrained to the specific CLI binary in the skill configuration. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input for tweets and direct messages in SKILL.md. Boundary markers are present as JSON input structures. The skill possesses capabilities for network operations via the belt CLI. No explicit sanitization or filtering is defined for the input content, though JSON formatting provides inherent structure.
Audit Metadata