ltx-director

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the AI agent to ingest, parse, and modify the timeline_data widget from external ComfyUI workflows, which creates a potential vector for malicious data to influence the agent's behavior.\n
  • Ingestion points: The agent retrieves untrusted workflow data containing hidden JSON strings through the get_workflow tool, as documented in the procedure section of SKILL.md.\n
  • Boundary markers: No explicit boundary markers or instructions to ignore potential commands within the timeline_data JSON are provided to the agent.\n
  • Capability inventory: The skill leverages tools like set_input and create_workflow to write modified states back to the application environment, allowing a potential payload in the input data to affect system configuration.\n
  • Sanitization: The instructions focus on structural validity (JSON parsing) but do not include content sanitization or validation of the segment prompts against injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 08:50 PM
Security Audit — agent-trust-hub — ltx-director