skills/notque/vexjoy-agent/design/Gen Agent Trust Hub

design

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown instructions and reference documentation for design workflows. No malicious patterns, obfuscation, or unauthorized capability requests were detected.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes user-provided inputs such as interview transcripts and design mockups.
  • Ingestion points: User-provided research transcripts, survey data, and UI descriptions are ingested in RESEARCH and CRITIQUE modes within SKILL.md.
  • Boundary markers: Absent; the skill does not define specific delimiters for separating user-supplied content from system instructions.
  • Capability inventory: The skill does not include any scripts or tools with high-privilege capabilities such as shell execution, file system modification, or network access.
  • Sanitization: The skill incorporates logical constraints in references/llm-design-failure-modes.md, requiring the agent to trace all findings to source evidence and explicitly mark assumptions, which provides a degree of protection against data-driven instruction overrides.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 08:54 PM
Security Audit — agent-trust-hub — design