twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
belt-sh/clitool vianpxand references installation documentation hosted on GitHub in theinference-sh/skillsrepository. - [COMMAND_EXECUTION]: Utilizes the
beltCLI tool to perform actions such as logging into services, posting content to Twitter/X, and generating images from HTML code. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection (Category 8) because it retrieves and processes content from external websites.
- Ingestion points: Web content accessed via
infsh/agent-browserand search results fromtavily/search-assistant. - Boundary markers: The instructions do not include specific delimiters or guardrails to prevent the agent from following malicious instructions that might be embedded in the external content it browses.
- Capability inventory: The agent has the capability to post to social media (
x/post-create) and run browser commands, which could be exploited if an external source influences the agent's output. - Sanitization: No explicit sanitization or validation of the content retrieved from external URLs is mentioned in the skill instructions.
Audit Metadata