Skip to content

Add CWE-Bench coding-agent security benchmark + Trent AI #20

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
v0id-space wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add CWE-Bench coding-agent security benchmark + Trent AI #20

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,6 +244,7 @@
- [OWASP Top 10 for Agentic Applications](https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/) - 2026 standard: agent goal hijacking, tool misuse, identity abuse, delegation risks.
- [NVIDIA Safety for Agentic AI](https://github.com/NVIDIA-AI-Blueprints/safety-for-agentic-ai) - Build/deploy/run safety patterns for agentic architectures.
- [Fortune: AI's Triple Act at Black Hat/DEF CON](https://fortune.com/2026/08/12/hacker-bodyguard-target-ais-triple-act-at-the-years-biggest-security-showdowns/) - Coverage of agent-to-agent interaction risks and shadow AI attack surfaces.
- [Trent AI](https://trent.ai/) - Specialized security agents in continuous loop that assess agentic systems against a repository threat model and track posture over time.

## 🖥️ OS and Endpoint Hardening

Expand Down Expand Up @@ -339,6 +340,7 @@
- [CSO Online: Industry Wakeup Call](https://www.csoonline.com/article/4136294/anthropics-claude-code-security-rollout-is-an-industry-wakeup-call.html) - Why Claude Code Security changes the AppSec landscape.
- [DataDome: MCP Prompt Injection Prevention](https://datadome.co/agent-trust-management/mcp-security-prompt-injection-prevention/) - Practical guide to stopping prompt injection in MCP deployments.
- [Lares: OWASP Agentic Top 10 in the Wild](https://labs.lares.com/owasp-agentic-top-10/) - Real-world threat examples mapped to OWASP Agentic categories.
- [Claude Code, Codex, Semgrep, CodeQL & Trent vs 28 CWE-Bench CVEs](https://trent.ai/blog/claude-code-codex-semgrep-codeql-trent-vs-cwe-bench-cve/) - Benchmark of five tools on 28 production CVEs across 22 repositories (XSS, path traversal, code/OS-command injection). Claude Code (Opus 4.7) surfaced the right vulnerability class 65% of the time but localized it to the patched file only 8.7% of the time.

## 🔄 Competitor and Adjacent Controls

Expand Down