ai-data-privacy

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured methodology for performing defensive privacy and data governance reviews based on industry standards like NIST AI RMF and OWASP.
  • [PROMPT_INJECTION]: The instructions include a specific safety notice that directs the agent to identify and flag prompt injection payloads found in reviewed content as findings, rather than following or executing them.
  • [COMMAND_EXECUTION]: The skill is restricted by its configuration to a limited set of tools (Read, Grep, Glob), which are appropriate for static analysis and auditing tasks.
  • [DATA_EXFILTRATION]: While the skill searches for sensitive information such as PII and API keys, this is performed within the context of a security audit to identify vulnerabilities in the target system. There are no mechanisms provided for transmitting this data to external or untrusted domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 01:36 PM
Security Audit — agent-trust-hub — ai-data-privacy