comfy-analyze

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection via the processing of untrusted workflow.json files.
  • Ingestion points: The tools comfy_read, comfy_trace, comfy_upstream, and comfy_downstream all ingest external JSON files.
  • Boundary markers: Absent. The instructions do not provide delimiters or warnings to the agent to disregard natural language instructions found within the JSON data.
  • Capability inventory: The skill allows for local file reading and the execution of a Python-based CLI tool (we_vibin.py).
  • Sanitization: Absent. There is no evidence of filtering or sanitization of the JSON content before it is processed or summarized by the agent.
  • Command Execution (SAFE): The skill provides CLI equivalents that execute a local script (python we_vibin.py). This is consistent with the skill's primary purpose and does not include risky flags or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM