image-edit

Fail

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The instructions for installing prerequisites include the command curl -fsSL https://runcomfy.com/install.sh | sh. Piping a remote script directly to a shell is a dangerous pattern that executes unverified code with user-level privileges.
  • [COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands, including a global package installation (npm i -g @runcomfy/cli) and the use of the runcomfy run command with complex, user-influenced JSON payloads.
  • [EXTERNAL_DOWNLOADS]: The skill fetches and executes a setup script from an external URL (https://runcomfy.com/install.sh) during the installation phase.
  • [PROMPT_INJECTION]: The skill's architecture presents a surface for indirect prompt injection attacks.
  • Ingestion points: The image_urls and images fields across all routing options accept arbitrary, untrusted HTTPS URLs (SKILL.md).
  • Boundary markers: There are no delimiters or explicit instructions used to separate the external data from the agent's logic.
  • Capability inventory: The skill has the capability to execute shell commands via the RunComfy CLI (SKILL.md).
  • Sanitization: There is no evidence of validation, sanitization, or filtering of the input URLs or the prompts that interpolate this data.
Recommendations
  • HIGH: Downloads and executes remote code from: https://runcomfy.com/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 30, 2026, 09:25 AM