Skip to content

feat(detector): implement AI data exfiltration detector (Epic 4-F3)#32

Open
KbWen wants to merge 8 commits into
mainfrom
feat/data-exfiltration
Open

feat(detector): implement AI data exfiltration detector (Epic 4-F3)#32
KbWen wants to merge 8 commits into
mainfrom
feat/data-exfiltration

Conversation

@KbWen

@KbWen KbWen commented Jun 15, 2026

Copy link
Copy Markdown
Owner

Implements the AI Data Exfiltration Detector (Epic 4-F3) to audit code for LLM prompt exfiltration, MCP tool leaks, and public web writes.

KbWen added 8 commits June 15, 2026 10:58
- Implemented DataExfiltrationDetector checking LLM prompt, MCP tool leaks, and public web writes.
- Added esprima AST fallback and Shannon entropy filters.
- Completed unit tests and coverage optimization (247 passes, 92% module coverage).
- Added logging for production observability readiness.

Reviewed-by: wen
…ypasses in silent installer

- Strip JS block comments, python docstrings, single line comments, and string literals before performing human-in-the-loop (HITL) indicators checks.
- Expand data exfiltration text scanner to dynamically extract balanced parenthesized blocks to support nested calls.
- Initialize has_mcp in JS/TS visitor and text scanner fallback dynamically from filename.
- Add test coverage for long entropy keys, nested parenthesized blocks, mcp filename heuristics, and docstring/comment HITL bypasses.

Reviewed-by: wen
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant