codebase-design

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected within the skill instructions.
  • [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any scripts, executables, or package dependencies, reducing the risk of runtime code execution attacks.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by reading external markdown files and local project code.
  • Ingestion points: The skill reads PRINCIPLES.md, VOCABULARY.md, MODULES.md, TYPESCRIPT.md, CLOUDFLARE.md, and EFFECT.md from the ../coding-standards/ directory, as well as existing project files during the local convention audit.
  • Boundary markers: Absent. The skill does not implement delimiters or specific instructions to ignore embedded prompts within the loaded standards files.
  • Capability inventory: The skill relies on file system read and write capabilities to perform audits and implement code changes.
  • Sanitization: None. The content from external coding standard files is accepted as authoritative without verification or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 01:18 PM
Security Audit — agent-trust-hub — codebase-design