fund-technical-route-writer

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or behaviors were identified. The skill is entirely composed of Markdown guidelines, templates, and a YAML configuration for text generation tasks.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes user-provided research content. 1. Ingestion points: Research objectives, content, and key problems provided via references/info_form.md. 2. Boundary markers: No delimiters are explicitly defined to separate user input from system instructions. 3. Capability inventory: The skill does not use any dangerous capabilities such as subprocess execution, dynamic code evaluation, file writing, or network access. 4. Sanitization: No input validation or filtering is performed on the user text. Given the lack of executable tools, this surface is assessed as SAFE.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 12:13 AM
Security Audit — agent-trust-hub — fund-technical-route-writer