candango-design

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: The skill is configured to read project-specific documentation from docs/agents/feature-design.md, docs/agents/feature-docs.md, AGENTS.md, and CLAUDE.md.
  • Boundary markers: Absent. No instructions are provided to the agent to treat the content of these files as untrusted data or to disregard embedded instructions.
  • Capability inventory: The skill performs file system discovery of design assets and delegates execution to other functional UI and design skills.
  • Sanitization: Absent. The content within these files is processed directly without filtering or validation to guide the agent's workflow.
  • [NO_CODE]: The skill consists of Markdown and YAML configuration files and does not include any executable scripts or source code.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 03:31 PM
Security Audit — agent-trust-hub — candango-design