gdpr-compliance

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill performs PII audits by scanning database schemas and application source code, creating an attack surface where malicious data could influence agent behavior.
  • Ingestion points: The skill reads user-supplied database schemas (Prisma, SQL) and application source code files.
  • Boundary markers: The instructions do not include specific delimiters or requirements to ignore instructions found within the scanned data.
  • Capability inventory: The agent reads external files and performs analysis, which involves high-level reasoning over untrusted text.
  • Sanitization: There is no requirement to sanitize or filter the content of the files before the agent processes them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:57 PM
Security Audit — agent-trust-hub — gdpr-compliance