Lucene search
+L

118 matches found

Kitploit
Kitploit
•added 2026/11/19 10:02 p.m.•41 views

clawk

Give a coding agent its own disposable Linux machine, not yours. -lightgrey Install · Quickstart · Why a VM? · How it works · Compared to · FAQ · Docs A coding agent is only useful when you let it actually do things: install packages, run the code it writes, start servers, use the network. On you...

6.5AI score
SaveExploits0References4
Kitploit
Kitploit
•added 2026/11/19 5:48 p.m.•48 views

T3MP3ST

🌩️ T3MP3ST 🌩️ ▄▄▄█████▓▓█████ ███▄ ▄███▓ ██▓███ ▓█████ ██████ ▄▄▄█████▓ ▓ ██▒ ▓▒▓█ ▀ ▓██▒▀█▀ ██▒▓██░ ██▒▓█ ▀ ▒██ ▒ ▓ ██▒ ▓▒ ▒ ▓██░ ▒░▒███ ▓██ ▓██░▓██░ ██▓▒▒███ ░ ▓██▄ ▒ ▓██░ ▒░ ░ ▓██▓ ░ ▒▓█ ▄ ▒██ ▒██ ▒██▄█▓▒ ▒▒▓█ ▄ ▒ ██▒░ ▓██▓ ░ ▒██▒ ░ ░▒████▒▒██▒ ░██▒▒██▒ ░ ░░▒████▒▒██████▒▒ ▒██▒ ░ ▒ ░░ ░░ ▒░ ░░...

6.3AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/11/19 4:16 p.m.•34 views

nah

expensive mistakes stop here a guard that blocks catastrophic agent actions nahguard.ai • what it blocks • how it compares • how it decides • install • extend • threat model claude code · codex · cursor · pi · + 11 more nah is a guard that sits in your coding agent's hook path and reads tool call...

6.2AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/11/19 4:00 p.m.•31 views

superpowers-evals

Superpowers Evals Behavioral eval lab for superpowers. Quorum drives real coding-agent CLIs Claude, Codex, Antigravity, Gemini, Kimi, OpenCode, Pi, and Copilot through a Gauntlet QA agent and grades them against scenario acceptance criteria plus deterministic post-checks. Code, CLI, paths, and...

6.5AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/11/19 3:33 p.m.•56 views

libretto

Libretto Libretto is a toolkit for building robust web integrations. It gives your coding agent a live browser and a token-efficient CLI to: Inspect live pages with minimal context overhead Capture network traffic to reverse-engineer site APIs Record user actions and replay them as automation...

6.3AI score
SaveExploits0References6
Kitploit
Kitploit
•added 2026/11/19 2:36 p.m.•30 views

yoloai

yoloAI Sandboxed runner for AI coding agents. No permission fatigue, no credentials in the box, no changes to your project until you approve them. AI coding agents work best with the guardrails off, and that's a terrible way to run them on your real machine. yoloAI gives the agent a disposable...

6.2AI score
SaveExploits0References7
Kitploit
Kitploit
•added 2026/11/19 2:18 p.m.•33 views

opencode-secure

The open source AI coding agent. Installation YOLO curl -fsSL https://opencode.ai/install | bash Package managers npm i -g opencode-ai@latest or bun/pnpm/yarn scoop install opencode Windows choco install opencode Windows brew install anomalyco/tap/opencode macOS and Linux recommended, always up t...

6.2AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/11/19 12:41 p.m.•31 views

toolbox

-Significant%20AI%2C%20fully%20reviewed-1f77b4 MCP-based application security testing tools for your coding agent. Not a scanner — a collaborative workbench. Agents struggle with UI and stateful APIs; you're good at both. Sectool lets you explore an application through its proxy while an agent...

6.2AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/11/19 12:37 p.m.•19 views

alter-zero

Alter Zero Give your terminal a coding agent. Read, build, debug, and review code with an agent that works alongside you. Use the same tools for cybersecurity research, technical investigation, and everyday automation. Quick start · Features · Model providers · Commands & shortcuts · Support ·...

6.4AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/11/16 9:23 p.m.•34 views

yolo-cage

yolo-cage: autonomous coding agents that do no harm You're a responsible engineer. You'd never just let an AI run roughshod through your most sensitive systems and codebases. That's why you'd never just shut off the safeguards for a tool like Claude Code. It asks permission for every dangerous...

6.5AI score
SaveExploits0References13
NVD
NVD
•added 2026/11/08 2:16 a.m.•10 views

CVE-2026-123498

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...

3.7CVSS0.00154EPSS
SaveExploits0References2
CVE
CVE
•added 2026/11/08 1:37 a.m.•18 views

CVE-2026-123498

Vikunja versions before 2.7.1 are vulnerable to a prompt injection vulnerability (CWE-1427). Project members with write access can inject malicious instructions by setting ProjectTitle or task descriptions that are rendered verbatim within a coding agent's authoritative instruction block. Specifi...

3.7CVSS5.9AI score0.00154EPSS
SaveExploits0References2
osv_cve
osv_cve
•added 2026/11/08 1:37 a.m.•17 views

CVE-2026-123498 Vikunja veans before 2.7.1 Prompt Injection via Project and Task Metadata

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...

2.1CVSS6AI score
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2026/11/08 1:37 a.m.•9 views

CVE-2026-123498 Vikunja veans before 2.7.1 Prompt Injection via Project and Task Metadata

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...

3.7CVSS5.9AI score0.00154EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/11/08 1:37 a.m.•27 views

EUVD-2026-119383

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...

3.7CVSS5.9AI score0.00154EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/11/08 1:37 a.m.•30 views

CVE-2026-123498 Vikunja veans before 2.7.1 Prompt Injection via Project and Task Metadata

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...

3.7CVSS0.00154EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/11/08 12:00 a.m.•10 views

PT-2026-139779

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...

3.7CVSS5.9AI score0.00154EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/11/08 12:00 a.m.•11 views

CVE-2026-123498: go-vikunja vikunja: Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to…

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...

3.7CVSS5.9AI score0.00154EPSS
SaveExploits0References1
osv_opensuse
osv_opensuse
•added 2026/11/04 12:00 a.m.•12 views

OPENSUSE-SU-2026:12421-1 pi-coding-agent-1.5.0-1.1 on GA media

These are all security issues fixed in the pi-coding-agent-1.5.0-1.1 package on the GA media of openSUSE Tumbleweed...

8.7CVSS6.3AI score0.00335EPSS
SaveExploits0References2
Packet Storm News
Packet Storm News
•added 2026/10/28 12:00 a.m.•19 views

CARI: Cross-Boundary Adversarial Runtime Injection in Coding-Agent Workflows

Coding agents increasingly develop, test, and integrate software whose components are owned by different developers, teams, or services. This exposes a distinct attack surface: a malicious or compromised peer development role can manipulate a live component of the software under development e.g.,...

5.7AI score
SaveExploits0
Rows per page
Query Builder