power-bi-model-review

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection]: The skill processes user-provided semantic model definitions, which presents an attack surface for instructions embedded in data. However, the lack of powerful tools or network access mitigates this risk.
  • Ingestion points: Step 1 in SKILL.md identifies the model definition input.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate the input data from the prompt context.
  • Capability inventory: The skill only performs text generation and DAX analysis, with no access to system commands or external APIs.
  • Sanitization: No explicit sanitization or validation logic is specified for the input model content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:56 PM
Security Audit — agent-trust-hub — power-bi-model-review