ai-image-generation

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (CRITICAL): The skill's documentation in SKILL.md explicitly recommends running curl -fsSL https://cli.inference.sh | sh. This pattern is highly dangerous as it downloads and executes a script from an untrusted external domain with shell privileges without any integrity verification.
  • EXTERNAL_DOWNLOADS (HIGH): The skill promotes the installation of a third-party CLI tool (infsh) and suggests using npx skills add to fetch additional remote modules from the inference-sh repository, none of which are on the trusted sources list.
  • COMMAND_EXECUTION (MEDIUM): The skill requests broad permissions via allowed-tools: Bash(infsh *), allowing the agent to execute any sub-command of the infsh utility. This provides a significant attack surface for potentially sensitive operations like infsh login or executing arbitrary remote apps.
  • PROMPT_INJECTION (LOW): The skill interpolates user-provided text directly into command-line arguments for image generation prompts. This creates a surface for indirect prompt injection if the inputs are not properly sanitized before being sent to the external API.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 18, 2026, 11:49 AM
Security Audit — agent-trust-hub — ai-image-generation