controlnet-pose

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @runcomfy/cli package from the official NPM registry. This is a standard and expected dependency for the skill's stated purpose.
  • [COMMAND_EXECUTION]: The skill uses the runcomfy CLI tool within a restricted Bash environment. The documentation explicitly warns against using unsafe shell execution patterns and provides guidance on avoiding shell injection by passing inputs as JSON strings.
  • [PROMPT_INJECTION]: The skill identifies potential indirect prompt injection risks associated with processing user-provided URLs for reference images and videos.
  • Ingestion points: External URLs for media files are passed via the --input argument as shown in SKILL.md.
  • Boundary markers: Documentation instructs the agent to only ingest URLs explicitly provided by the user.
  • Capability inventory: The skill's capabilities are focused on interacting with the RunComfy Model API via the CLI, with file writes limited to a designated output directory.
  • Sanitization: The skill highlights that the CLI does not perform shell expansion on prompt content, reducing the risk of malicious payload execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:10 AM
Security Audit — agent-trust-hub — controlnet-pose