NVIDIA-NeMo / NVIDIA-NeMo/Guardrails
[Security] Logging Captures Sensitive LLM Outputs - Data Leak
Open
Beginner friendly
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 842
- Avg merge
- 3d 1h
- Merged PRs (30d)
- 25
Description
Description
Debug logs capture full LLM outputs including potentially sensitive data. Logs exposed to unauthorized users.
Expected Behavior
Don't log LLM outputs. Or hash/redact sensitive parts.
Actual Behavior
File: src/logging/logger.py
Logs everything: logger.debug(f"LLM output: {output}")
GSSoC Points Estimate: Level 2 (Security)
Suggested Labels
- gssoc:approved
- type:bug
- severity:high
- area:security
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with src/logging/logger.py and inspect the debug logging of the LLM output. Determine whether outputs should be omitted or protected through hashing or redaction, then verify that sensitive LLM content is no longer exposed in debug logs.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- security
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 68/100