roadshow-material-preparation

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of Markdown-based instructions and templates designed to guide the agent through financial material preparation. No executable scripts (.sh, .py, .js) are included.
  • [DATA_EXFILTRATION]: The skill references a local configuration file (../../CLAUDE.md) to gather project context. This is a standard practice for scene-level configuration in specific agent environments and does not involve unauthorized access to sensitive system paths (e.g., SSH keys, AWS credentials) or network exfiltration.
  • [PROMPT_INJECTION]: The instructions follow a professional financial reporting structure. There are no attempts to bypass safety filters, override system instructions, or use adversarial role-play techniques.
  • [EXTERNAL_DOWNLOADS]: No external URLs, remote scripts, or package installations were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:26 AM
Security Audit — agent-trust-hub — roadshow-material-preparation