twitter-thread-creation

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command-line tool to perform actions like posting to Twitter/X, generating images from HTML, and browsing the web. These operations are consistent with the skill's stated purpose of social media content creation and utilize the vendor's own infrastructure.
  • [EXTERNAL_DOWNLOADS]: The instructions suggest installing additional skills from the inference-sh organization via npx. These are trusted vendor resources within the author's ecosystem and do not pose an external dependency risk.
  • [DATA_EXPOSURE]: While the skill includes tools for web browsing and search (agent-browser, search-assistant), it does not access sensitive local files or hardcoded credentials. All network operations are performed through the vendor's defined toolset.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:26 AM