twitter-automation

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command-line interface to interact with the Twitter/X API through the inference-sh platform. The allowed-tools configuration correctly restricts the agent's capability to this specific toolset.
  • [EXTERNAL_DOWNLOADS]: Includes instructions for installing supplementary agent skills from the official inference-sh/skills repository using the npx skills add command.
  • [PROMPT_INJECTION]: The skill processes external data such as tweet text and media URLs provided via JSON input.
  • Ingestion points: Input parameters for x/post-tweet and x/post-create in SKILL.md.
  • Boundary markers: None explicitly defined within the input structure.
  • Capability inventory: Tool access to infsh for social media posting and interaction with other platform apps (e.g., Image/Video generation).
  • Sanitization: Not specified in the static instructions; the skill relies on the underlying platform's handling of the input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 10:44 PM