Personal data sent to the model without redaction
HighAV-DATA-004Secrets & data exposureCore packNew in 2.0
What it finds
Fields like SSN, card number, date of birth, passport or medical data are put into a model prompt with no redaction step.
Why it matters
Prompts are often logged, cached, and kept by providers. Sending raw personal data widens who can see it and can break privacy rules (GDPR, HIPAA, PCI).
What an attacker could do: Sensitive personal data leaves your system in every request.
How to fix it
Redact or tokenize personal fields before they reach the prompt, and only send what the task needs.
Pro shows the corrected code for your exact file, step by step, and re-scans to confirm the fix. See plans
Check details
- Finding code
- PII_SENT_TO_MODEL
- How it detects
- Looks for a risky pattern, and stays quiet when a matching safeguard is present.
- Confidence
- Likely: strong signal, but review it in context.
- Scans
- Any text-based agent source or configuration (JS/TS/Python/JSON/YAML)
- OWASP LLM Top 10
- LLM06 - Sensitive Information Disclosure
- NIST AI RMF
- MS-2.10
- SOC 2
- C1.1, P4.1
Check your agent for this
Paste your agent code or MCP config. The free scan runs all 124 checks in about 10 seconds — no account needed.
Related checks
- Hardcoded credentials (generic pattern)AV-SECRET-001 · Critical
- Credential or secret placed in the system promptAV-DATA-002 · High
- Data exfiltration path: private data + untrusted input + outbound channelAV-DATA-003 · High
- Credential stored in plain text in the MCP configAV-MCP-102 · High
- All environment variables handed to an MCP serverAV-MCP-111 · High
- Sensitive values written to logsAV-DATA-001 · Medium