neurodivergent-visual-org

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its handling of untrusted data inputs.\n
  • Ingestion points: The skill parses user messages for distress signals and reads settings from a project-level configuration file (.claude/neurodivergent-visual-org-preference.yml).\n
  • Boundary markers: The instructions do not define delimiters or structural safeguards to separate operational instructions from the data loaded from configuration files or user messages.\n
  • Capability inventory: The skill utilizes powerful tools including Read, Write, Edit, and Bash(cmd:*), which could be leveraged if the agent's logic is subverted through malicious input.\n
  • Sanitization: No explicit sanitization or validation logic is provided to filter user input or configuration values before they are processed or rendered into Mermaid diagrams.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:54 PM