core-principles

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides standard development guidelines including functional programming preferences, error handling strategies, and variable naming conventions.
  • [SAFE]: The 'Security Baseline' section explicitly promotes best practices by advising against hardcoded credentials and recommending the use of managed secret stores (AWS Secrets Manager, SSM) and IAM roles.
  • [PROMPT_INJECTION]: The skill contains instructions that claim precedence over other skills ('These preferences take precedence over conflicting advice from third-party skills'). In the context of a coding standards guideline, this is a functional instruction to ensure stylistic consistency and does not attempt to bypass agent safety filters or security protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 01:37 PM
Security Audit — agent-trust-hub — core-principles