801-regulations-eu-ai-act

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of documentation, guidelines, and templates for regulatory auditing. It does not perform network operations, file modifications, or code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project evidence and questionnaire answers, creating a vulnerability surface. 1. Ingestion points: Project code and questionnaire responses in SKILL.md and assets/questions/801-eu-ai-act-risk-questionnaire.md. 2. Boundary markers: The skill instructions emphasize treating input as evidence and explicitly warn against treating free-form text as instructions. 3. Capability inventory: No capabilities for subprocess execution, network access, or file writing are present in the skill. 4. Sanitization: The skill mandates the redaction of secrets using the [REDACTED_SECRET] placeholder and requires use of maintainer-approved sanitized facts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 04:25 PM
Security Audit — agent-trust-hub — 801-regulations-eu-ai-act