design-companion

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, command execution, or unauthorized network activity were found. The skill content is purely instructional. The reference to 'pm-workspace-docs/research/human-centric-ai-design-research.md' is a documentation link and does not involve sensitive data.
  • [NO_CODE]: The skill does not contain any executable scripts or software dependencies.
  • [PROMPT_INJECTION]: The skill acts as a design review tool which processes user-provided content. (Ingestion points: design briefs in SKILL.md. Boundary markers: absent. Capability inventory: none. Sanitization: absent). While the skill lacks boundaries for untrusted data, it possesses no active capabilities, resulting in no identifiable security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:31 PM