csv-pii-scanner

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the skill instructions and Python script confirms it operates as a standard local data processing tool with no detected malicious behaviors.
  • [DATA_EXFILTRATION]: The script reads from a user-provided input path and writes to a user-provided output path. No unauthorized data transfer or hardcoded credentials were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted CSV data. It includes a redaction function (redact) that sanitizes potential PII before it is included in the output JSON, mitigating data leakage risks for downstream consumers.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 04:04 PM
Security Audit — agent-trust-hub — csv-pii-scanner