Projects tagged with “prompt-injection”
Browse Jev GitHub projects tagged with prompt-injection. Filter, sort and explore their source repositories.
- 294jev-cliCommand-line tool for TypeSafe's Jev AI model
Nasrallah-AL/jev-cli · TypeScript
233clifact-checkingguardrailsllm-toolsnodejsprompt-injection - Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside DeepSeek Harness.
HorusJiang/dsh-jev-tools · TypeScript
132context-windowdeepseek-harnessdshdsh-pluginllmprompt-injection - 645jevossEvaluation tools for Jev-compatible decision models, covering accuracy, calibration, hidden instructions, padding and consistency.
mertkayacs/jevoss · Python
51benchmarkcalibrationdecision-modelevaluationllm-evaluationprompt-injectionpython - 707jev-shieldSemantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.
caiovicentino/jev-shield · JavaScript
40javascriptai-safetymcpprompt-injection - Grok Bot skills that hand an agent's small decisions (search, mail, triage, routing) to TypeSafe's Jev. Fail-open.
fal3/grokbot-jev-skills · Python
11agent-skillsai-agentsgrok-botllm-toolsprompt-injectionpython - 1221jev-adrankReal-time ad ranking and creative review on a typed evaluation model — one call prices a whole auction, no trained CTR model, no logged clicks.
leepokai/jev-adrank · JavaScript
10ad-rankingadsauctionbrand-safetyecpmprompt-injectionreal-time - 1237jev-bouncerClaude Code plugin: a 3-cent bouncer for your agent's shell. Jev typed probabilities auto-allow routine commands, deny destructive ones, and flag prompt injection in tool results.
alsoleg89/jev-bouncer · Python
10agent-securityai-agentsclaude-codeclaude-code-pluginhooksprompt-injection - 1784dsh-jev-lensJev quality bench for DeepSeek Harness: shadow-accounted dangerous-command judging, injection screening, canary A/B drills, optional gate mode.
jackchen13755/dsh-jev-lens · TypeScript
00agent-safetycordisdeepseek-harnessdshdsh-pluginprompt-injection - Screening LLM agent tool output for relevance and prompt injection with Jev, a hosted System One classifier. Harness, test beds, run records and analysis.
zacharytgray/jev-context-filter-harness · Python
00agent-securityagentdojocontext-managementllm-agentsllm-evaluationprompt-injectiontoken-efficiency - 2081Jev-DefenseA Jev-powered security guard for AI agents: blocks dangerous tool calls, strips prompt injection, scans skills. Works with Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, and OpenCode.
prestonkakukdev/Jev-Defense · Python
00ai-agentsai-safetyclaude-codeguardrailsllm-securityprompt-injectionpython - Jev (TypeSafe AI System One) 生态调研:开源复现规模、JevBench v1.4.2.2 全量解读、可获取性与许可证陷阱、router 生态、Jev+安全科研切入点
freezetheflame/jev-ecosystem-research · HTML
00ai-securitybenchmarkdecision-modelllm-routerprompt-injectionragpython - 2178jev-guardStatic code scanner (SAST linter) that finds insecure usage of Jev / TypeSafe guardrails in Python. Not a guardrail itself — build-time analysis, offline, no API key.
ppradyoth/jev-guard · Python
00ai-securitycode-scanningguardrailslangchainlinterllm-securityprompt-injection
1–12 of 12