056-design-avoid-breaking-changes

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected in this skill. The skill's behavior is consistent with its stated goal of performing compatibility reviews.
  • [PROMPT_INJECTION]: The skill contains defensive instructions specifically designed to prevent indirect prompt injection. In references/056-design-avoid-breaking-changes.md, the 'SOURCE BOUNDARY' constraint explicitly tells the agent to treat reviewed artifacts as data and not to obey any instructions found within them.
  • [COMMAND_EXECUTION]: The skill suggests the use of standard local development tools such as the Maven Wrapper (./mvnw), xmllint, and openspec. These tools are used for their intended purpose of validating project builds and XML schemas within the user's local repository environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 05:56 PM
Security Audit — agent-trust-hub — 056-design-avoid-breaking-changes