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 the belt-sh/cli package using npx. 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 like tavily/search-assistant and infsh/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 login and post content to X (Twitter) using belt 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
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — twitter-thread-creation