-
Notifications
You must be signed in to change notification settings - Fork 0
tslit.stub
id: tslit name: TSLIT (Time-Shift LLM Integrity Tester) repo_path: ~/Documents/sw30labs/repos/tslit remote_url: https://github.com/sw30labs/tslit.git primary_language: Python framework: LangGraph + llama-cpp-python ingested: 2026-04-11 last_commit_date: 2026-04-11 category: ai-security stacks: [langgraph, pentest]
Sandboxed evaluation harness for detecting time-based latent behaviors and affiliation bias in local non-US-origin LLMs served through native llama.cpp runtimes. Tests 32 scenarios across 15 probe dates (~3,840 interactions) to surface logic bombs, affiliation bias, censorship, and telemetry injection.
CLI entry via Typer (src/tslit/cli.py). Campaign runner executes scenario×date matrix against a test model via llama-cpp-python. 12 threat detectors run per interaction. Results logged as NDJSON artifacts. A separate multi-agent LLM Analyzer (Ollama-backed) with AnalyzerAgent + QAManagerAgent validates findings in a loop. Reports generated as JSON and text.
Core: typer, rich, pydantic, pyyaml, python-dotenv, llama-cpp-python. Analysis: langchain, langchain-core, langchain-community, langgraph, scipy, numpy. Dev: pytest, black, ruff.
No CI workflows. No Docker.
- pentest-regulatory-intel (shared pentesting/security domain)
- agentic-ai-pentesting (shared AI pentesting research)
- strixresearch (autonomous pentesting research)
- Tags: [python, langgraph, llm, security, local-inference, pentesting]