Rubric Builder

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the instructions and metadata revealed no malicious patterns, command executions, or data exfiltration attempts.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from user-provided assignments and objectives (SKILL.md, Step 1). While it lacks boundary markers and sanitization for these inputs, the capability inventory is limited to generating text-based rubric tables with no access to dangerous tools or scripts, mitigating the risk of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 01:40 AM
Security Audit — agent-trust-hub — Rubric Builder