canvas-design

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The "FINAL STEP" section contains a simulated user instruction: "The user ALREADY said 'It isn't perfect enough. It must be pristine...'" This technique attempts to override the model's standard operational mode by fabricating conversation history to force high-effort behavior.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through user-provided design inputs.
  • Ingestion points: User input provided at the start of the "DESIGN PHILOSOPHY CREATION" process.
  • Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands within the user input.
  • Capability inventory: The skill creates .md, .pdf, and .png files, and involves executing code to generate visual assets.
  • Sanitization: Absent; no validation or filtering is applied to the user input before it influences the generated philosophy and artwork.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 05:31 PM