Agentic-Security-Code-Review

🔍 Agentic Security Code Review !Claude Codehttps://img.sh...

agent-api-server (>=2.1.7, <=2.1.13), agentc-langchain (1.0.0) +5 more potentially affected by CVE-2026-34070 via langchain-core (0.3.76)

langchain-core PYPI version 0.3.76 is affected by a known vulnerability. The following packages have a transitive dependency on langchain-core and may be impacted: - agent-api-server =2.1.7, =0.0.2, =0.3.0, =1.0.0rc1, =0.0.91, =0.0.118 Source cves: CVE-2026-34070 Source advisory: OSV:PYSEC-2026-2...

tolstoy-agents (>=0.1.29, <=0.1.49) potentially affected by CVE-2026-34070 via langchain-core (0.2.35)

langchain-core PYPI version 0.2.35 is affected by a known vulnerability. The following packages have a transitive dependency on langchain-core and may be impacted: - tolstoy-agents =0.1.29, =0.1.49 Source cves: CVE-2026-34070 Source advisory: OSV:PYSEC-2026-2193...

PT-2026-29362

Name of the Vulnerable Software and Affected Versions AVideo versions 26.0 and prior Description The AVideo platform, an open source video platform, has an issue in the CreatePlugin template for list.json.php in versions 26.0 and prior. This template lacks authentication and authorization checks...

24/7 Payments for 24/7 Agents: The Case for Crypto in the Machine Economy

Crypto enables 24/7 payments for AI agents, replacing fiat limits with scalable machine-to-machine transactions and powering the emerging machine economy...

Optimizing Risk Discovery and Remediation with Qualys Gateway Service (QGS)

Unpatched vulnerabilities remain one of the largest drivers of cyber risk, accounting for nearly 60% of cyber compromises. Modern security programs are therefore measured not only by how quickly they discover risk, but also by how efficiently they remediate it. As organizations scale vulnerabilit...

Exploit for Command Injection in Paloaltonetworks Pan-Os

CVE KB: A high-quality knowledge base for automatic penetratio...

test-xss

test-xss "test." Install bash np...

Server-side Template Injection

giskard-agents is vulnerable to server-side template injection. The vulnerability is due to the ChatWorkflow.chat method passing its string argument directly to a non‑sandboxed Jinja2 Environment, where the input string is treated as a template by inlineenv.fromstring and an attacker can supply...

Improper Neutralization of Special Elements Used in a Template Engine

Overview giskard-agents is an A lightweight library that orchestrates LLM completions and agents in parallel workflows Affected versions of this package are vulnerable to Improper Neutralization of Special Elements Used in a Template Engine via the ChatWorkflow.chat function. An attacker can...

tolstoy-agents (>=0.1.29, <=0.1.49) potentially affected by CVE-2026-34070 via langchain-core (0.2.35)

langchain-core PYPI version 0.2.35 is affected by a known vulnerability. The following packages have a transitive dependency on langchain-core and may be impacted: - tolstoy-agents =0.1.29, =0.1.49 Source cves: CVE-2026-34070 Source advisory: OSV:GHSA-QH6H-P6C9-FF54...

agent-api-server (>=2.1.7, <=2.1.13), agentc-langchain (1.0.0) +5 more potentially affected by CVE-2026-34070 via langchain-core (0.3.76)

langchain-core PYPI version 0.3.76 is affected by a known vulnerability. The following packages have a transitive dependency on langchain-core and may be impacted: - agent-api-server =2.1.7, =0.0.2, =0.3.0, =1.0.0rc1, =0.0.91, =0.0.118 Source cves: CVE-2026-34070 Source advisory:...

UNIX Symbolic Link (Symlink) Following

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to UNIX Symbolic Link Symlink Following via the agents.create and agents.update processes. An attacker can append arbitrary content to files outside the intended workspace by planting a...

OpenClaw: Symlink Traversal via IDENTITY.md appendFile in agents.create/update (Incomplete Fix for CVE-2026-32013)

Summary The patch for CVE-2026-32013 introduced symlink resolution and workspace boundary enforcement for agents.files.get and agents.files.set. However, two other handlers in the same file agents.create and agents.update still use raw fs.appendFile on the IDENTITY.md file without any symlink...

CVE-2026-4516

A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of the file metagpt/actions/di/writeanalysiscode.py of the component DataInterpreter. The manipulation results in injection. It is possible to launch the attack remotely. The exploit has be...

CVE-2026-32013

OpenClaw versions prior to 2026.2.25 contain a symlink traversal vulnerability in the agents.files.get and agents.files.set methods that allows reading and writing files outside the agent workspace. Attackers can exploit symlinked allowlisted files to access arbitrary host files within gateway...

@grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool

Impact The knowledgesearch and knowledgegetnode MCP tools are included in SCOPEDTOOLS visible to scoped agents but their handlers do not receive authContext and do not enforce workspace scoping. A scoped agent in Workspace A can supply an arbitrary workspaceId parameter to search or retrieve...

GHSA-647H-P824-99W7 @grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool

Impact The knowledgesearch and knowledgegetnode MCP tools are included in SCOPEDTOOLS visible to scoped agents but their handlers do not receive authContext and do not enforce workspace scoping. A scoped agent in Workspace A can supply an arbitrary workspaceId parameter to search or retrieve...

Introducing Wiz Workflows: Your path to building a self healing cloud

Orchestrate customizable workflows with agents, enabling end-to-end discovery and response in Wiz...

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents through Skills, Plugins, and Watchers

Whitepaper called ClawKeeper: Comprehensive Safety Protection For OpenClaw Agents Through Skills, Plugins, And Watchers...