data-breach-blast-radius
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill is designed to perform security audits and proactively inventory sensitive data such as PII, PHI, and credentials. While it explicitly searches for configuration files (.env), database schemas, and identity data, these operations are consistent with its primary function and are fully disclosed in the execution workflow.
- [EXTERNAL_DOWNLOADS]: The skill references official reports from IBM and legal documentation from government entities (e.g., cnil.fr, hhs.gov, and official EU/US legislative sites). These are well-known, trusted sources used solely for data classification benchmarks and regulatory fine calculations.
- [PROMPT_INJECTION]: No override markers, role-play instructions, or attempts to bypass agent safety filters were identified. The instructions use professional framing to define the agent's role as a breach impact expert.
- [DATA_EXFILTRATION]: No unauthorized network operations or credential harvesting patterns were found. Sensitive data found during analysis remains within the generated report context for the user.
Audit Metadata