prismor v1.38.0

Prismor Runtime security hooks for Claude Code, Codex, and other AI coding agents. Prismor can also be used in observe mode to see agent session activity and dangerous actions in a local self-serve dashboard Website • Onboard with Skill !Trae / Trae CNht...

EUVD-2026-52434

Shlink contains a blind SQL injection vulnerability that allows any authenticated API key holder to inject arbitrary SQL fragments by supplying an unvalidated direction value in the orderBy query parameter of the tag statistics endpoint. Attackers can craft a malicious direction string containing...

CVE-2026-18733 Prompt injection bypasses shell tool consent gate in Strands Agents Tools

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

CVE-2026-18733

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

EUVD-2026-52432

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

spotlight

Spotlight by CMUL8 The AI security engineer. Phase 1 MVP — ve...

prismor v1.37.0

Prismor Runtime security hooks for Claude Code, Codex, and other AI coding agents. Prismor can also be used in observe mode to see agent session activity and dangerous actions in a local self-serve dashboard Website • Onboard with Skill !Trae / Trae CNht...

screenpipe app-v2.5.167

DOWNLOAD SCREENPIPE screenpipe | YC S26 Screenpipe remembers how you actually work Record your screen continuously locally and provide context to your agents Claude, Codex, Openclaw, Hermes, Runner... https://github.com/user-attachments/assets/70fe94eb-6d2a-47ca-b7c3-c8ead13a5b7f news 06/10 - we...

PT-2026-67502

Name of the Vulnerable Software and Affected Versions Amazon Strands Agents Tools versions prior to 0.8.0 Description A prompt injection issue in the shell tool allows remote actors to execute arbitrary operating system commands on the agent host. This is achieved by using a crafted prompt that...

CVE-2026-18733: Undefined Security Weakness

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

Invisible Ink Threats: Adversarial Goals behind Legitimate Tasks in Computer-Use Agents

Computer-use agents CUAs, which empower large language models to autonomously operate operating systems and the web, are increasingly vulnerable to indirect prompt injection attacks. A widely adopted defense is the human-in-the-loop paradigm, in which the agent pauses for explicit user confirmati...

pkgxray v1.0.5

pkgxray — pre-install security for npm packages, MCP servers, and AI agents Inspect an npm package or MCP server before you install or connect to it, and get a deterministic, evidence-backed SAFE, REVIEW, or BLOCK verdict. Local, zero-dependency static analysis — normal scans never execute packag...

Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments

Coding agents increasingly run inside organizations whose security controls scoped credentials, restricted egress, read-only filesystems, non-root execution constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is...

AlmaLinux 8 : fence-agents (ALSA-2026:47736)

The remote AlmaLinux 8 host has packages installed that are affected by a vulnerability as referenced in the ALSA-2026:47736 advisory. httplib2: httplib2: Denial of Service via unbounded decompression of HTTP response bodies CVE-2026-59939 Tenable has extracted the preceding description block...

@inkeep/agents-core (>=0.0.0-dev-20260106221934, <=0.41.0), @inkeep/ai-sdk-provider (>=0.0.0-dev-20260106221934, <=0.41.0) +10 more potentially affected by CVE-2026-67328 via @better-auth/sso (>=1.3.28, <=1.6.20)

@better-auth/sso NPM version =1.3.28, =0.0.0-dev-20260106221934, =0.0.0-dev-20260106221934, =0.0.0-dev-20260106221934, =7.5.0-canary.1, =7.5.0-canary.1, =1.0.0, =0.1.0, =0.1.0, =1.3.0, =3.1.2, =0.8.13, =0.9.0 Source cves: CVE-2026-67328 Source advisory: SNYK:JS-BETTERAUTHSSO-18508069...

fence v0.1.65

Fence wraps commands in a sandbox that blocks network access by default and restricts filesystem operations based on configurable rules. It's most useful for running semi-trusted code package installs, build scripts, CI jobs, unfamiliar repos with controlled side effects, and it can also compleme...

RHSA-2026:48585 Red Hat Security Advisory: fence-agents security update

Bulletin has no description...

EUVD-2026-51722

The Fluent Support WordPress plugin before 2.3.1 does not perform a per-ticket access check before reassigning a ticket's customer, allowing a restricted support agent to change the assigned customer of any ticket in the system, including tickets outside their granted scope...

CVE-2026-18394

Incorrect authorization in the httprequest tool in Strands Agents Tools before 0.8.2 might allow remote attackers to obtain credentials configured via HTTPREQUESTTOKENCONFIG by influencing the LLM to route requests through actor-controlled proxy infrastructure. To remediate this issue, users shou...

EUVD-2026-51623

Incorrect authorization in the httprequest tool in Strands Agents Tools before 0.8.2 might allow remote attackers to obtain credentials configured via HTTPREQUESTTOKENCONFIG by influencing the LLM to route requests through actor-controlled proxy infrastructure. To remediate this issue, users shou...