swan-design

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides purely instructional content for technical writing and visual design using ASCII characters. No evidence of prompt injection, credential access, or malicious command execution was found.
  • [SAFE]: All references within the skill (such as spec-template.md and ears-format.md) are local files focused on documentation patterns. There are no external downloads or remote script executions.
  • [SAFE]: The skill uses design metaphors and specific writing constraints (the "Grove voice") which are stylistic in nature and do not attempt to bypass safety filters or override core agent instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:31 AM