show-complexity

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of natural language instructions for performing architectural analysis and code reviews. No malicious patterns, credential harvesting, or unauthorized network operations were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze project source code and documentation, which constitutes a surface for indirect prompt injection. However, the instructions are limited to complexity assessment and visualization. There are no high-risk capabilities mentioned, such as arbitrary command execution or data exfiltration, that would provide an exploit path for injected instructions.
  • Ingestion points: Project files, package documentation, and file inventories.
  • Boundary markers: None specified for input data.
  • Capability inventory: Generation of text-based diagrams (Mermaid) and HTML artifacts for visualization.
  • Sanitization: No explicit sanitization or escaping of external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 08:17 PM