twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches instructions from a remote GitHub repository at
https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.- [REMOTE_CODE_EXECUTION]: The instructions direct the user to install thebelt-sh/clipackage usingnpx. This involves the execution of code from an external source.- [INDIRECT_PROMPT_INJECTION]: The skill includes functionality to search the web and browse webpages using tools liketavily/search-assistantandinfsh/agent-browser. The output is used to generate social media content, which presents a surface for indirect prompt injection attacks. - Ingestion points: Web search results and webpage screenshots/content ingested via external tools.
- Boundary markers: Absent; the skill does not specify delimiters or warnings to ignore instructions found within the retrieved data.
- Capability inventory: The skill can perform authenticated operations through
belt loginand post content to X (Twitter) usingbelt app run x/post-create. - Sanitization: Absent; content fetched from the internet is used directly in thread generation without prior validation or filtering.
Audit Metadata