multi-advisor

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for persona emulation and response synthesis. No malicious patterns, obfuscation, or sensitive data access were detected.
  • [PROMPT_INJECTION]: The skill processes untrusted user input which represents a surface for indirect prompt injection. However, this is managed through structured templates and does not escalate the risk beyond standard interaction.
  • Ingestion points: User question (SKILL.md)
  • Boundary markers: Clear Markdown headers and structured synthesis sections are used to delimit responses.
  • Capability inventory: Tools listed in frontmatter (claude-code, antigravity, cursor, gemini-cli, codex-cli) provide standard development capabilities.
  • Sanitization: No explicit sanitization of user questions is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 07:05 PM