2d-parallax

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied visual assets and design intent, which establishes a potential surface for indirect injection via untrusted data.\n
  • Ingestion points: User-provided source artwork, shot purpose, and subject descriptions as defined in the Workflow section of SKILL.md.\n
  • Boundary markers: No specific delimiters or safety instructions are defined to separate user content from the agent's instructions.\n
  • Capability inventory: The skill defines design principles and does not grant the agent capabilities for shell command execution, network access, or file system modifications.\n
  • Sanitization: The skill does not implement validation or filtering of user-provided content.\n- [EXTERNAL_DOWNLOADS]: The skill references historical and technical documentation in references/2d-parallax.md. All links target official domains of well-known organizations, such as Adobe and the Walt Disney Family Museum, and are intended for research purposes without automated execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 12:49 PM