Full prompts or conversations written to logs
MediumAV-DATA-005Audit & loggingCore packNew in 2.0
What it finds
Whole prompts or conversation histories are logged.
Why it matters
Conversations contain whatever users typed — passwords, personal details, private documents. Logs are kept longer and seen by more people than the data itself.
What an attacker could do: Anyone with log access can read users' conversations.
How to fix it
Log IDs, sizes and outcomes instead of full text. If you must log content, redact it and keep it for a short, fixed time.
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
- FULL_PROMPT_LOGGING
- 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, CC7.2
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.