relight

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @runcomfy/cli package from the official npm registry. This is a legitimate dependency required for the skill's core functionality and originates from the service provider's verified namespace.
  • [COMMAND_EXECUTION]: Shell command execution is strictly limited to the runcomfy CLI tool through the allowed-tools frontmatter configuration. This implementation of least privilege prevents the agent from executing unauthorized system commands.
  • [DATA_EXFILTRATION]: The skill documentation provides clear guidance on secure credential management, detailing the storage of API tokens with restricted file permissions (0600) and the use of environment variables in automated environments.
  • [PROMPT_INJECTION]: The skill uses structured JSON boundaries (via the --input flag) when passing user-provided content to the CLI, effectively preventing shell injection. Additionally, the documentation explicitly identifies potential risks from third-party image metadata and provides guidance on safe handling of external assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 07:38 AM
Security Audit — agent-trust-hub — relight