056-design-avoid-breaking-changes
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes a 'SOURCE BOUNDARY' constraint in its reference documentation that serves as a defensive measure against indirect prompt injection. It explicitly instructs the agent to treat external inputs such as GitHub issues, PR notes, and specifications as data and to ignore any instructions embedded within those artifacts that conflict with the skill's own rules.
- [COMMAND_EXECUTION]: The skill workflow recommends the use of standard local validation utilities including Maven (
mvn),xmllint, andnpmscripts. These recommendations are limited to verifying the integrity of the repository using documented developer workflows and do not involve unauthorized or suspicious command execution.
Audit Metadata