0xbyt4 127a4e512b security: redact secrets from auxiliary and vision LLM responses ...

LLM responses from browser snapshot extraction and vision analysis
could echo back secrets that appeared on screen or in page content.
Input redaction alone is insufficient — the LLM may reproduce secrets
it read from screenshots (which cannot be text-redacted).

Now redact outputs from:
- _extract_relevant_content (auxiliary LLM response)
- browser_vision (vision LLM response)
- camofox_vision (vision LLM response)

2026-04-01 12:03:56 -07:00

78 KiB

Raw Blame History

View Raw