Lucene search
+L

23 matches found

Kitploit
Kitploit
•added 2026/11/21 8:33 p.m.•33 views

skillscript

Safe, reusable automation authored by agents. skillscript.ai • docs TL;DR — npm install -g skillscript-runtime && skillfile init && skillfile dashboard. See Quickstart. What is Skillscript? Skillscript came from asking: what would a Makefile look like if it built skills instead of binaries? The...

6.8AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/11/21 12:05 p.m.•47 views

MakerChecker

🛡️ MakerChecker The open-source security layer for AI agents. Deny-by-default enforcement, human approvals, and a cryptographically signed audit trail — so your agent runs only what it's granted and provably can't approve its own work. Website · Live Demo · mc scan · Docs Your agents keep running...

6.3AI score
SaveExploits0References17
Kitploit
Kitploit
•added 2026/11/20 4:52 p.m.•32 views

OneAlert

OneAlert AI Security OS Open-source autonomous cyber defense for industrial networks AI agents that detect, investigate, hunt, and respond to threats across your OT/ICS infrastructure — with human approval gates and full audit trails. Demo Setup · Features · Quick Start · Architecture Try It Now...

6.2AI score
SaveExploits0References1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/11/16 12:00 a.m.•5 views

CVE-2026-83817: codewhale-hq CodeWhale: CodeWhale is a DeepSeek and MiMo coding agent for the terminal

CodeWhale is a DeepSeek and MiMo coding agent for the terminal. Prior to 0.9.0, DEFAULTAUTOMATIONAUTOAPPROVE caused AutomationRecord::taskautoapprove to resolve an omitted setting to true, and the automationcreate schema advertised the same insecure default. enqueueruntask converted that omission...

7.5CVSS6.2AI score0.00509EPSS
SaveExploits0References3
osv_cve
osv_cve
•added 2026/11/09 9:02 p.m.•10 views

CVE-2026-123812 Dynatrace MCP Server: create_dynatrace_notebook missing the human-approval gate

Dynatrace MCP Server is an MCP server for Dynatrace Observability. Prior to 1.8.7, the createdynatracenotebook registration in src/index.ts performs a persistent document-write action without calling requestHumanApproval, although the project's other write tools use that gate to obtain operator...

3.7CVSS6.2AI score
SaveExploits0References5
Vulnrichment
Vulnrichment
•added 2026/11/09 9:02 p.m.•7 views

CVE-2026-123812 Dynatrace MCP Server: create_dynatrace_notebook missing the human-approval gate

Dynatrace MCP Server is an MCP server for Dynatrace Observability. Prior to 1.8.7, the createdynatracenotebook registration in src/index.ts performs a persistent document-write action without calling requestHumanApproval, although the project's other write tools use that gate to obtain operator...

3.7CVSS6.2AI score0.00297EPSS
SaveExploits0References3
Cvelist
Cvelist
•added 2026/11/09 9:02 p.m.•28 views

CVE-2026-123812 Dynatrace MCP Server: create_dynatrace_notebook missing the human-approval gate

Dynatrace MCP Server is an MCP server for Dynatrace Observability. Prior to 1.8.7, the createdynatracenotebook registration in src/index.ts performs a persistent document-write action without calling requestHumanApproval, although the project's other write tools use that gate to obtain operator...

3.7CVSS0.00297EPSS
SaveExploits0References3
Packet Storm News
Packet Storm News
•added 2026/11/08 12:00 a.m.•9 views

Treating the Model As an Untrusted Component: Deterministic Policy Enforcement, Human Approval and Taint Tracking against Prompt Injection in Tool-Using Agents, with Validation on Open-Weights Models

Tool-using LLM agents act on instructions embedded in the data they read, so prompt injection is a structural rather than a prompt-wording problem. We compare in-prompt defences hardened prompts, spotlighting, LLM detectors with deterministic enforcement outside the model four reference monitors ...

5.9AI score
SaveExploits0
Vulnrichment
Vulnrichment
•added 2026/11/05 4:35 p.m.•6 views

CVE-2026-54141 OpenHuman: Yuanbao non-web channel can bypass human approval to execute `node_exec`

OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, a remote direct message received through a configured Yuanbao channel is converted into a generic channel AgentTurnRequest that uses the default tool policy without establishing an...

9CVSS6.4AI score0.00492EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/11/05 4:35 p.m.•35 views

CVE-2026-54141 OpenHuman: Yuanbao non-web channel can bypass human approval to execute `node_exec`

OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, a remote direct message received through a configured Yuanbao channel is converted into a generic channel AgentTurnRequest that uses the default tool policy without establishing an...

9CVSS0.00492EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/11/05 4:35 p.m.•16 views

CVE-2026-54141 OpenHuman: Yuanbao non-web channel can bypass human approval to execute `node_exec`

OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, a remote direct message received through a configured Yuanbao channel is converted into a generic channel AgentTurnRequest that uses the default tool policy without establishing an...

9CVSS6.4AI score
SaveExploits0References6
CVE
CVE
•added 2026/11/05 4:35 p.m.•26 views

CVE-2026-54141

The OpenHuman agent harness (desktop application and Rust library) is vulnerable to a code injection and missing authorization flaw in versions prior to 0.57.13 . A remote direct message received via a configured Yuanbao channel is converted into an AgentTurnRequest using the default tool policy ...

9CVSS6.4AI score0.00492EPSS
SaveExploits0References4
Kitploit
Kitploit
•added 2026/08/08 6:34 a.m.•21 views

skillscript v0.39.2

Safe, reusable automation authored by agents. skillscript.ai • docs TL;DR — npm install -g skillscript-runtime && skillfile init && skillfile dashboard. See Quickstart. What is Skillscript? Skillscript came from asking: what would a Makefile look like if it built skills instead of binaries? The...

6.4AI score
SaveExploits0References9
Kitploit
Kitploit
•added 2026/08/07 5:40 p.m.•22 views

skillscript v0.39.1

Safe, reusable automation authored by agents. skillscript.ai • docs TL;DR — npm install -g skillscript-runtime && skillfile init && skillfile dashboard. See Quickstart. What is Skillscript? Skillscript came from asking: what would a Makefile look like if it built skills instead of binaries? The...

6.4AI score
SaveExploits0References9
Github Security Blog
Github Security Blog
•added 2026/07/29 3:36 p.m.•25 views

@dynatrace-oss/dynatrace-mcp-server's create_dynatrace_notebook missing the human-approval gate

Summary A missing human-approval gate on the createdynatracenotebook tool allows a caller to create persistent tenant-visible documents containing arbitrary content including embedded DQL that other users execute when opening the notebook without operator consent. Details dynatrace-mcp-server...

6.2AI score
SaveExploits0References5Affected Software1
Positive Technologies
Positive Technologies
•added 2026/07/29 12:00 a.m.•8 views

PT-2026-69225

Summary A missing human-approval gate on the create dynatrace notebook tool allows a caller to create persistent tenant-visible documents containing arbitrary content including embedded DQL that other users execute when opening the notebook without operator consent. Details dynatrace-mcp-server...

3.7CVSS6.3AI score
SaveExploits0References6
Kitploit
Kitploit
•added 2026/07/20 3:50 p.m.•15 views

skillscript v0.36.1

Safe, reusable automation authored by agents. skillscript.ai • docs TL;DR — npm install -g skillscript-runtime && skillfile init && skillfile dashboard. See Quickstart. What is Skillscript? Skillscript came from asking: what would a Makefile look like if it built skills instead of binaries? The...

6.4AI score
SaveExploits0References9
Positive Technologies
Positive Technologies
•added 2026/07/01 12:00 a.m.•40 views

PT-2026-55225

Name of the Vulnerable Software and Affected Versions FlowDrop versions 0.0.0 through 1.6.0 Description A missing authorization issue allows forceful browsing. The module, which enables testing and running AI-driven workflows via a chat interface, fails to sufficiently re-evaluate human-in-the-lo...

5.4CVSS5.8AI score0.0023EPSS
SaveExploits0References9
GithubExploit
GithubExploit
•added 2026/04/17 5:52 p.m.•132 views

cruxss-bb-agent

CRUXSS Bug Bounty Agent A semi-autonomous bug bounty hunting...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/03/12 12:00 a.m.•24 views

AEGIS: No Tool Call Left Unchecked -- a Pre-Execution Firewall and Audit Layer for AI Agents

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer with no framework-agnostic control point in between...

6AI score
SaveExploits0
Rows per page
Query Builder