discover-architecture

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate functionality for architectural analysis through source code inspection.
  • [PROMPT_INJECTION]: No direct prompt injection instructions were found. The skill reads external codebase content, creating a surface for indirect prompt injection, but its instructions are limited to structural analysis.
  • Ingestion points: Source code files via Read and Grep.
  • Boundary markers: None.
  • Capability inventory: Bash, Read, Grep, Glob.
  • Sanitization: None.
  • [DATA_EXFILTRATION]: No hardcoded credentials or access to sensitive system file paths were detected.
  • [EXTERNAL_DOWNLOADS]: The skill does not download external packages or scripts.
  • [COMMAND_EXECUTION]: Use of Bash and Grep is confined to repository exploration and code analysis tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 05:37 PM