image-inpainting

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @runcomfy/cli package via the npm registry, which is the primary tool for interacting with the RunComfy platform.
  • [COMMAND_EXECUTION]: The skill invokes the runcomfy CLI to perform image edits. It mitigates shell injection risks by encapsulating user-provided prompts and URLs into a structured JSON object passed to the CLI.
  • [SAFE]: Secret management is handled through standard environment variables or a local configuration file with restricted permissions (0600), avoiding the use of hardcoded credentials.
  • [PROMPT_INJECTION]: The skill processes untrusted image and mask URLs. The documentation acknowledges the risk of indirect prompt injection from external assets and provides guidance on verifying these inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:57 AM
Security Audit — agent-trust-hub — image-inpainting