🛡️SCR-Bench evaluates security risks in LLM agent skill ecosystems: skills that appear benign in isolation can become harmful in composition. Three sub-benchmarks — 🔄SCR-CapFlow, 🪪SCR-TrustLift, 🔐SCR-AuthBlur — show composed paths expose risks invisible under isolated review.
☆17Jun 21, 2026Updated 4 months ago
Alternatives and similar repositories for SCR_Bench
Users that are interested in SCR_Bench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Nov 19, 2025Updated 11 months ago
- ☆15Dec 18, 2025Updated 10 months ago
- Accepted to ACL'25 (main)☆12May 19, 2025Updated last year
- X-ray any Claude Code skill instantly. SkillScope parses any SKILL.md and renders it as an interactive flowchart — triggers, steps, tool…☆15Feb 20, 2026Updated 8 months ago
- ☆53Mar 24, 2026Updated 7 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- From Prompt Injection to Persistent Control: Defending Agentic Workspaces Against Trojan Backdoors☆21Sep 22, 2026Updated last month
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆51Jun 1, 2026Updated 4 months ago
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- Stack Overflow but for AI agents☆18Apr 17, 2026Updated 6 months ago
- Codes for our paper "AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems"☆14Dec 13, 2024Updated last year
- Official implementation of "HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety"☆21Aug 19, 2026Updated 2 months ago
- ☆24Oct 22, 2026Updated last week
- Code and data for study: "Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories"☆16May 5, 2026Updated 5 months ago
- ECCV2026 -Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos☆34Sep 2, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [EMNLP2026 Findings] TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories☆20Sep 7, 2026Updated last month
- ☆60May 19, 2026Updated 5 months ago
- Backdooring Neural Code Search☆14Sep 8, 2023Updated 3 years ago
- Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness☆19Jul 17, 2025Updated last year
- ☆35May 22, 2025Updated last year
- On the Robustness of GUI Grounding Models Against Image Attacks☆12Apr 8, 2025Updated last year
- To solve 'image generation failed: network error' issue from latest Codex version. Delegate imagegen to stable version @openai/codex@0.14…☆18Aug 2, 2026Updated 2 months ago
- ☆12Nov 14, 2021Updated 4 years ago
- ☆35Aug 22, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Source Code Search☆13Nov 16, 2023Updated 2 years ago
- ABAP Code Analyzer☆13Sep 26, 2026Updated last month
- Deterministic safety floor for tool-using AI agents: pre-execution gating, SafeFix suggestions, attack-chain detection, opt-in self-learn…☆30Sep 1, 2026Updated last month
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆41Sep 17, 2025Updated last year
- Source code implementation of "LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks (MM24)"☆15Mar 30, 2026Updated 7 months ago
- ☆29Aug 31, 2025Updated last year
- [ACL 2026 Main] ACIArena: Toward Unified Evaluation for Agent Cascading Injection☆16Aug 9, 2026Updated 2 months ago
- SHE: Trajectory-driven Safety Harness Evolution for LLM Agents☆22Aug 4, 2026Updated 2 months ago
- Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing☆15Feb 18, 2021Updated 5 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models☆14Nov 22, 2024Updated last year
- ☆15Dec 12, 2023Updated 2 years ago
- The official training code of SingProbe.☆36Sep 3, 2026Updated last month
- "SALLM: Security Assessment of Generated Code" accepted at ASYDE workshop co-located with ASE'24.☆18Jul 21, 2026Updated 3 months ago
- AHA is autoresearch for agent safety: one agent red-teams a production agent overnight and comes back with reusable explanations of why t…☆37Sep 26, 2026Updated last month
- PGD adversarial training in PyTorch☆12Sep 4, 2019Updated 7 years ago
- [EMNLP 2025] VideoEraser: Concept Erasure in Text-to-Video Diffusion Models☆14Nov 23, 2025Updated 11 months ago