Highlights
- Pro
Popular repositories Loading
-
PERMANENT-opencode-anthropic-oauth-fix
PERMANENT-opencode-anthropic-oauth-fix PublicDrop-in patched dist/index.js for op-anthropic-auth@0.1.1: fixes Anthropic third-party classifier 400s and /messages vs /v1/messages path mismatch in opencode
-
opencode-anthropic-max-fix
opencode-anthropic-max-fix PublicFixes Claude Pro/Max 429 / out-of-credit errors in opencode by installing op-anthropic-auth@0.1.1 with OAuth billing headers, pinning it in config, and watching for bun-install overwrites
-
llm-firewall-v2
llm-firewall-v2 PublicPrompt-injection firewall with a shadow-mode discipline: detectors must meet a measured false-positive budget on real traffic before they may block. Layered OWASP-LLM01 detectors + promotion gate.
Python 1
-
ghidra-llm-copilot
ghidra-llm-copilot PublicAn LLM copilot for reverse engineering built around one truth: decompiled code is attacker-controlled and the copilot is a prompt-injection surface. A naive copilot is hijacked into calling malware…
Python 1
-
malware-family-classifier
malware-family-classifier PublicML malware family classifier with structural binary analysis, TF-IDF strings, and LLM enrichment
Python 1
If the problem persists, check the GitHub status page or contact support.



