twitter-automation

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Employs the infsh command-line utility to execute Twitter/X operations such as posting, liking, and retweeting through the inference.sh platform ecosystem.
  • [EXTERNAL_DOWNLOADS]: References official installation and integration documentation hosted on the vendor's GitHub repository and domain (inference-sh).
  • [PROMPT_INJECTION]: Identified as having a surface for indirect prompt injection (Category 8). The skill takes text inputs that are subsequently broadcast to a public social media platform.
  • Ingestion points: Command-line arguments in SKILL.md (e.g., --input '{"text": "..."}').
  • Boundary markers: Employs JSON structure for data input which acts as a basic delimiter.
  • Capability inventory: Possesses write access to external social media accounts via infsh app run x/post-tweet and x/dm-send.
  • Sanitization: The instructions do not specify any validation or sanitization routines for the input text before it is transmitted to the Twitter/X API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 01:18 PM