seedance-style

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and mapping tables designed to guide an AI agent in generating visual style descriptors.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it processes untrusted user input to generate prompts.
  • Ingestion points: User requests for visual styles, art direction, and period aesthetics (SKILL.md description and Intent section).
  • Boundary markers: Absent. The skill does not define specific delimiters for separating user input from system instructions.
  • Capability inventory: No file system access, network operations, or subprocess calls were identified in the skill scripts or instructions.
  • Sanitization: The skill includes an explicit 'Style Safety Rule' that instructs the agent to sanitize input by rewriting IP-sensitive franchise or creator names into descriptive, safe visual anchors.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:42 AM
Security Audit — agent-trust-hub — seedance-style