twitter-automation

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh CLI, which is the official tool provided by the vendor (inference-sh-9), to perform various Twitter/X operations such as posting, liking, and following. This is standard behavior for a CLI-based integration skill.
  • [EXTERNAL_DOWNLOADS]: Mentions the use of npx skills add to install related tools. This is a standard mechanism for extending agent capabilities within this ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for tweets and prompts for AI generation (e.g., image and video creation). While these are ingestion points for potentially untrusted data, the risk is inherent to the primary function of social media automation and content generation. Standard agent guardrails for output validation are recommended.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:47 AM