balanced-scorecard

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill follows secure design principles by requiring human approval for AI-generated metrics and documenting data provenance to prevent 'dashboard theatre'.
  • [INDIRECT_PROMPT_INJECTION]: The skill recognizes the risk of ingesting untrusted external data (strategy statements, mission descriptions). It mitigates this by requiring agents to classify the source confidence (stated, provisional, inferred) and using provenance blocks to track data origin, though the risk is inherent to any data-processing skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:51 AM
Security Audit — agent-trust-hub — balanced-scorecard