pair-design

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of Markdown methodology guides, JSON/Markdown templates, and example session transcripts. It does not include any executable scripts, binary files, or installation commands.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill references external URLs targeting the author's GitHub repositories (e.g., github.com/mary13/pair-design-agent-skill and github.com/mary13/tailor-onboarding). These are consistent with the author's context and serve as legitimate resources for the skill's methodology.
  • [INDIRECT_PROMPT_INJECTION]: While the skill defines a workflow where the agent ingests external input (design requirements from a human collaborator), this is the primary intended function of the design methodology. The instructions do not involve high-risk automated actions based on untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 10:27 AM
Security Audit — agent-trust-hub — pair-design