pico2-swd-riscv

pico2-swd-riscv SWD debug probe for RP2350 RISC-V Hazard3 cores. One Pico2 debugs another via two GPIO wires. 0. VIBE CODE WARNING WRITTEN BY HUMAN About 80% of the code is vibe coded; The readme is almost completely generated except the whole vibe-code-warning section. I spent many nights with...

kern

kern: rootless container runtime and sandbox with no daemon. Runs agent tool calls and LLM-generated code in kernel-enforced containers. A real, kernel-enforced container in a few milliseconds, out of one static binary with no daemon. MCP support for Claude Code, Cursor, Claude Desktop and LM...

synaptic-sentinel

SYNAPTIC Sentinel The vibe-coding security sentinel. An Apache-2.0 agentic security toolkit for projects where most of the code is written by AI. Five deterministic scouts catch the syntactic problems; a Brain Layer BYOK Anthropic decides what really matters and how to fix it — all inside the IDE...

aigate

aigate Secret hygiene for AI-generated code. Catches hardcoded credentials in prompts, tool inputs, generated code, and existing files. Quick start pip install aigate && aigate setup-all That's it. This installs a background proxy redact mode, a PostToolUse hook for file scanning, and registers t...

cso-vibecheck

cso-vibecheck ██████╗███████╗ ██████╗ ██╗ ██╗██╗██████╗ ███████╗ ██╔════╝██╔════╝██╔═══██╗ ██║ ██║██║██╔══██╗██╔════╝ ██║ ███████╗██║ ██║ ██║ ██║██║██████╔╝█████╗ ██║ ╚════██║██║ ██║ ╚██╗ ██╔╝██║██╔══██╗██╔══╝ ╚██████╗███████║╚██████╔╝ ╚████╔╝ ██║██████╔╝███████╗ ╚═════╝╚══════╝ ╚═════╝ ╚═══╝...

Newer and Bigger, but Safer? A Longitudinal Study of the Functionality-Security Gap in LLM-Generated Code

Large Language Models LLMs are widely used to generate code. Although their functional plausibility keeps improving, the generated code often contains security vulnerabilities. The functionality-security gap captures code that passes functional tests but fails security tests. A recent longitudina...

What Is the Difference between Me and You? Benchmarking the Quality Gap between Human-Written and AI-Generated Code

AI coding assistants are becoming co-authors of production software, yet their evaluation centers on functional correctness, leaving open whether their code differs from human code in the quality dimensions dominating lifecycle cost. We compare human-written and AI-generated code at scale: 787,56...

LLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production Repositories

Large language models LLMs are increasingly used to generate and assist with software development, yet existing vulnerability datasets largely focus on human-written code or controlled prompting environments. This limits the ability to study security weaknesses in LLM-generated code as it appears...

Prompt Structure Redistributes, Not Reduces: An Empirical Analysis of Security-Weaknesses in LLM-Generated Python Code

Large Language Models LLMs increasingly generate code from natural-language prompts, making prompt engineering a key mechanism for shaping the security of generated software. Structured and security-oriented prompts are widely used to encourage safer code, yet their effects extend beyond whether...

Wiz Red Agent Finds Its Way Into Snowflake’s Internal Jira Through a Flaw in a GitHub Copilot–Assisted PR

Wiz Red Agent independently discovered and exploited a GitHub Actions injection missed by GitHub’s Advanced Security, validated access to sensitive data in Snowflake’s internal Jira, and assessed the blast radius—all without human intervention, five days after the flaw became live...

IBM Langflow OSS Code Execution Vulnerability (CNVD-2026-32369)

IBM Langflow OSS is the open-source version of Langflow that IBM officially integrates and promotes. IBM Langflow OSS has a code execution vulnerability. This vulnerability stems from the failure to properly handle components generated by the LLM during the Agentic Assistant validation process. T...

Arbitrary Code Injection

Overview flowise is a Flowiseai Server Affected versions of this package are vulnerable to Arbitrary Code Injection via the run method in the CSVAgents class. An attacker can execute arbitrary code in the context of the server process by sending crafted prompts to a chatflow using the CSV Agent...

`datamodel-code-generator` vulnerable to code injection via unescaped carriage return in GraphQL Union description

Summarydatamodel-code-generator is vulnerable to code injection when generating Python models from an attacker-controlled GraphQL schema. A description on a Union type, written in the regular-string form "..." with a literal \r escape, is rendered into a Python comment by a Jinja2 filter that...

GHSA-386Q-5HP3-95M9 `datamodel-code-generator` vulnerable to code injection in via attacker-controlled `default_factory` schema field

Summary datamodel-code-generator is vulnerable to code injection when generating Python models from an attacker-controlled JSON Schema, OpenAPI, YAML, JSON, Avro, Protobuf, or XSD schema. When a property carries a "defaultfactory" key, its value is interpolated verbatim — as a raw Python expressi...

GHSA-3HRF-2GC2-MX32 Microsoft Kiota: XML Doc-Comment Newline Breakout Code Injection

Summary Kiota versions prior to 1.32.3 and 1.29.1 are affected by a code-generation injection vulnerability in the C XML documentation-comment sink the description, externalDocs label, and externalDocs link fields emitted as /// … comments. When text from an OpenAPI description is written into...

Microsoft Kiota: XML Doc-Comment Newline Breakout Code Injection

Summary Kiota versions prior to 1.32.3 and 1.29.1 are affected by a code-generation injection vulnerability in the C XML documentation-comment sink the description, externalDocs label, and externalDocs link fields emitted as /// … comments. When text from an OpenAPI description is written into...

Security Vulnerability Patterns in AI-Generated Code: A Cross-Model Comparative Study

LLM-based coding tools enable non-expert users to generate routine automation scripts that may enter enterprise workflows without meaningful security review. This study examines that risk directly. Code was collected from ChatGPT, Microsoft Copilot, and Google Gemini using identical prompts acros...

oapi-codegen: OpenAPI Server Description Escapes Generated Go Comment and Injects Executable Code

Summary The vulnerability in oapi-codegen seems to be similar with CVE-2026-22785, which is a generated-code injection issue where untrusted OpenAPI summary text is embedded into generated TypeScript MCP server source without proper escaping. oapi-codegen has a similar vulnerability in its server...

PYSEC-2026-562 vanna vulnerable to remote code execution caused by prompt injection

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in...

CVE-2026-44291

A flaw was found in protobufjs, a library that compiles protobuf definitions into JavaScript functions. This prototype pollution vulnerability occurs when Object.prototype is polluted, allowing attacker-controlled properties to be resolved as valid protobuf type information. This can lead to...