CVE-2026-95985

The file write tool in Amazon Kiro IDE versions before 1.0.242 might allow remote unauthenticated actors to inject crafted instructions into the agent's context. When a user runs the agent in a crafted repository as an untrusted workspace, sending any message can cause agent modifications to...

CVE-2026-95985

Versions of Amazon Kiro IDE prior to 1.0.242 are vulnerable to an issue where the file write tool allows remote unauthenticated actors to inject crafted instructions into the agent's context. By running the agent in a crafted repository designated as an untrusted workspace , an attacker can cause...

CVE-2026-95985 Kiro IDE Allows Agentic Writes to Global Configurations While Working in Untrusted Workspaces

The file write tool in Amazon Kiro IDE versions before 1.0.242 might allow remote unauthenticated actors to inject crafted instructions into the agent's context. When a user runs the agent in a crafted repository as an untrusted workspace, sending any message can cause agent modifications to...

CVE-2026-95985 Kiro IDE Allows Agentic Writes to Global Configurations While Working in Untrusted Workspaces

The file write tool in Amazon Kiro IDE versions before 1.0.242 might allow remote unauthenticated actors to inject crafted instructions into the agent's context. When a user runs the agent in a crafted repository as an untrusted workspace, sending any message can cause agent modifications to...

EUVD-2026-86308

The file write tool in Amazon Kiro IDE versions before 1.0.242 might allow remote unauthenticated actors to inject crafted instructions into the agent's context. When a user runs the agent in a crafted repository as an untrusted workspace, sending any message can cause agent modifications to...

CVE-2026-95985: Inclusion of Functionality from Untrusted Control Sphere

The file write tool in Amazon Kiro IDE versions before 1.0.242 might allow remote unauthenticated actors to inject crafted instructions into the agent's context. When a user runs the agent in a crafted repository as an untrusted workspace, sending any message can cause agent modifications to...

PT-2026-98205

Name of the Vulnerable Software and Affected Versions Amazon Kiro IDE versions prior to 1.0.242 Description The file write tool allows remote unauthenticated actors to inject crafted instructions into the agent's context. This occurs when a user runs the agent within a crafted repository as an...

Directory Traversal

Overview mcp-atlassian is a The Model Context Protocol MCP Atlassian integration is an open-source implementation that bridges Atlassian products Jira and Confluence with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with...

CVE-2026-82020 Hermes Agent 0.16.0 < 0.17.0 Credential Store Overwrite via File-Write Tool

Hermes Agent 0.16.0 prior to 0.17.0 contains an improper path restriction vulnerability that allows attackers who can influence ingested message content to overwrite the credential store by bypassing sensitive-path guards that excluded the auth.json file. Attackers can craft malicious messages...

CVE-2026-82020

Hermes Agent versions 0.16.0 through prior to 0.17.0 contain an improper path restriction vulnerability. Sensitive-path guards that should protect the credential store failed to exclude the auth.json file , allowing an attacker who can influence ingested message content to craft a malicious messa...

CVE-2026-82020 Hermes Agent 0.16.0 < 0.17.0 Credential Store Overwrite via File-Write Tool

Hermes Agent 0.16.0 prior to 0.17.0 contains an improper path restriction vulnerability that allows attackers who can influence ingested message content to overwrite the credential store by bypassing sensitive-path guards that excluded the auth.json file. Attackers can craft malicious messages...

CVE-2026-82020 Hermes Agent 0.16.0 < 0.17.0 Credential Store Overwrite via File-Write Tool

Hermes Agent 0.16.0 prior to 0.17.0 contains an improper path restriction vulnerability that allows attackers who can influence ingested message content to overwrite the credential store by bypassing sensitive-path guards that excluded the auth.json file. Attackers can craft malicious messages...

CVE-2026-10591

Insufficient access control restrictions in the file write tool in Amazon Kiro IDE before version 0.11 might allow remote unauthenticated actors to execute arbitrary commands via crafted instructions that cause writes to execution-sensitive paths such as .vscode/tasks.json, enabling auto-executio...

CVE-2026-10591

Insufficient access control restrictions in the file write tool in Amazon Kiro IDE before version 0.11 might allow remote unauthenticated actors to execute arbitrary commands via crafted instructions that cause writes to execution-sensitive paths such as .vscode/tasks.json, enabling auto-executio...

CVE-2026-10591

Insufficient access control restrictions in the file write tool in Amazon Kiro IDE before version 0.11 might allow remote unauthenticated actors to execute arbitrary commands via crafted instructions that cause writes to execution-sensitive paths such as .vscode/tasks.json, enabling auto-executio...

PT-2026-45768

Name of the Vulnerable Software and Affected Versions Amazon Kiro IDE versions prior to 0.11 Description Insufficient access control restrictions in the file write tool allow remote unauthenticated actors to execute arbitrary commands. This is achieved by using crafted instructions to write to...

CVE-2026-10591: Incorrect Permission Assignment for Critical Resource

Insufficient access control restrictions in the file write tool in Amazon Kiro IDE before version 0.11 might allow remote unauthenticated actors to execute arbitrary commands via crafted instructions that cause writes to execution-sensitive paths such as .vscode/tasks.json, enabling auto-executio...

CVE-2026-43992: Exposure of Sensitive Information to an Unauthorized Actor

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...

Spring AI Agentic Patterns (Part 3): Why Your AI Agent Forgets Tasks (And How to Fix It)

Have you ever asked an AI agent to perform a complex multi-step task, only to find it skipped a critical step halfway through? You're not alone. Research shows that LLMs struggle with "lost in the middle" failures—forgetting tasks buried in long contexts. When your agent juggles file edits, test...

Arbitrary SQL Execution

Neuron is vulnerable to arbitrary SQL execution. The vulnerability is due to the MySQLWriteTool executing caller‑provided SQL using PDO::prepare and execute without semantic restrictions, where an attacker can inject destructive statements such as DROP TABLE, TRUNCATE, DELETE, or ALTER via...