decision-toolkit

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious code, credential exposure, or dangerous command execution patterns were found. The skill primarily acts as a template generator for decision-making analysis.
  • [EXTERNAL_DOWNLOADS]: The interactive HTML guide template (templates/decision-guide-template.html) references external stylesheets from Google Fonts (fonts.googleapis.com). This is a common practice for web typography and uses a well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of potentially untrusted data to populate its templates.
  • Ingestion points: SKILL.md explicitly lists meeting transcripts, user notes, and existing documents as primary context sources (Step 1: Gather Context).
  • Boundary markers: The templates in templates/ use standard double-brace placeholders (e.g., {{CONTEXT}}) for interpolation but do not include explicit instructions to ignore potentially malicious instructions embedded in the input data.
  • Capability inventory: The skill is restricted to text generation (Markdown, HTML, script templates) and does not possess capabilities for file system modification, network exfiltration, or shell command execution.
  • Sanitization: The skill relies on the underlying model's safety constraints and does not provide custom sanitization logic for external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 08:42 PM