data-minimisation

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves a defensive purpose, educating users on how to reduce data collection to improve privacy and compliance.- [EXTERNAL_DOWNLOADS]: The skill includes links to 'frontendchecklist.io', a well-known resource for web development best practices.- [PROMPT_INJECTION]: The skill analyzes external code for privacy audits. This constitutes a surface for indirect prompt injection (Category 8); however, the skill's capabilities are limited to providing feedback and explanations, posing no high-severity risk. Evidence: (1) Ingestion points: Codebase components and API calls in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: Analysis and reporting only. (4) Sanitization: Not applicable for this scope.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 12:29 AM
Security Audit — agent-trust-hub — data-minimisation