sticky-synthesis

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized network activity were detected in the skill instructions. The logic is strictly focused on content synthesis and organization within a design context.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (sticky notes) from Figma Design files or text inputs, creating a surface for indirect prompt injection. However, the synthesis focus and lack of dangerous tools mitigate this risk.
  • Ingestion points: Figma sticky notes or supplied text content (SKILL.md).
  • Boundary markers: None specified to delimit input content from instructions.
  • Capability inventory: The skill can read from and propose/apply edits (groupings and labels) to the Figma Design canvas if the environment supports it.
  • Sanitization: No explicit content filtering or sanitization is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:31 AM
Security Audit — agent-trust-hub — sticky-synthesis