planetscale-query-insights-and-tags

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable code or scripts, functioning solely as a set of analytical instructions.
  • [SAFE]: Privacy is prioritized by instructions that specifically warn against the use of sensitive data (e.g., secrets, tokens, user IDs) in database tags.
  • [SAFE]: Safety rules are implemented to prevent the agent from performing administrative tasks or code modifications without explicit user approval.
  • [PROMPT_INJECTION]: The skill processes external database query metadata, creating a surface for indirect prompt injection. However, it lacks tools or command execution capabilities to act on untrusted data.
  • Ingestion points: PlanetScale Insights API endpoints for query fingerprints and metrics.
  • Boundary markers: Absent.
  • Capability inventory: The skill defines no shell, file-write, or network-send tools.
  • Sanitization: Not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 06:27 AM
Security Audit — agent-trust-hub — planetscale-query-insights-and-tags