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.mdexplicitly recommends runningcurl -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 usingnpx skills addto fetch additional remote modules from theinference-shrepository, 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 theinfshutility. This provides a significant attack surface for potentially sensitive operations likeinfsh loginor 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