Agentic / MCP
435 entries
Every Agentic / MCP entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
CISA orders feds to prioritize patching Langflow auth bypass flaw
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) gave federal agencies until Friday to patch an actively exploited vulnerability in the Langflow visual framework for building AI agents...
@better-auth/oauth-provider's OAuth authorization-code grant allows concurrent redemption when two token requests race the find-then-delete primitive
### Am I affected? Users are affected if all of the following are true: - Their project depends on `@better-auth/oauth-provider` at a version `>= 1.6.0, < 1.6.11`, or uses the embedded plugin in `be...
Better Auth has stored XSS in the auth-server origin via javascript: redirect_uri in oidc-provider and mcp
### Am I affected? Check each condition. Users are affected when all of the first three hold. - Their application enables the `oidc-provider` plugin or the `mcp` plugin from `better-auth/plugins`. T...
@aborruso/ckan-mcp-server: SSRF via base_url allows access to internal networks (Potential fix bypass of CVE-2026-33060)
### Summary A known vulnerability CVE-2026-33060 indicated tools including ckan_package_search and sparql_query that accept a base_url parameter had the risk of making HTTP requests to arbitrary endpo...
Public GitHub Issue Could Trick GitHub Agentic Workflows Into Leaking Private Repo Data
A public issue can trick GitHub Agentic Workflows into leaking the contents of an organization's private repositories, researchers at Noma Security have shown. The attacker needs only to open a norma...
⚡ Weekly Recap: Proxy Botnets, Browser Ransomware, AI Agent Tricks, Fake PoC Malware and More
A streaming box should not need a threat model. Neither should a username field, a demo repo, a reset flow, or a browser permission prompt. That is the irritating part this week: the risky pieces were...
Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments
Researchers uncovered two campaigns embedding indirect prompt injections in malicious websites to exploit autonomous AI agents browsing the web. The post Prompt Injection Attacks Trick AI Agents Into...
CVE-2026-44934: A information disclosure when DEBUG loglevel is set in SUSE Rancher AI Agent 1.0 before 1.0.2 could leak API keys or LLM
A information disclosure when DEBUG loglevel is set in SUSE Rancher AI Agent 1.0 before 1.0.2 could leak API keys or LLM response text with potential sensitive data into logfiles, allowing local attac...
SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing
Scanners meant to catch malicious add-on "skills" for AI coding agents can be fooled by a few simple changes that leave the malware working, according to a new study from researchers at the Hong Kong...
JadePuffer ransomware used AI agent to automate entire attack
Researchers identified what they believe is the first documented case of a ransomware operation, JadePuffer, conducted entirely by a large language model (LLM) agent. [...]
CVE-2026-13341: A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow
A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute un...
Agentic AI Used to Conduct Ransomware Attack via Langflow
Attack demonstrates how LLM agents can combine known exploitation techniques with real-time reasoning to automate complex, multi-stage intrusions. The post Agentic AI Used to Conduct Ransomware Attack...
CVE-2026-52830: fast-mcp-telegram is a Telegram MCP Server. Prior to 0.19.1, fast-mcp-telegram validates HTTP Bearer tokens by joining t
fast-mcp-telegram is a Telegram MCP Server. Prior to 0.19.1, fast-mcp-telegram validates HTTP Bearer tokens by joining the raw token string into a session-file path. The verifier rejects the exact res...
Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)
## Summary Authorization for scoped (agent) MCP callers is enforced **inline, per tool**, and is applied inconsistently — several mutating tools silently omit the ancestry/workspace check that their...
Langroid: Path traversal in the file tools allows read/write outside configured current directory
### Summary Langroid's `ReadFileTool` and `WriteFileTool` appear to treat `curr_dir` as the intended working-directory boundary for file operations. However, the tools only change the process working...
mcp-memory-service: Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete
## Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete ### Summary All HTTP routes under `/api/documents/*` in `mcp-memory-service` are served without an...
Identity Lifecycle Management Wasn't Built for AI Agents
Identity lifecycle management was architected around a person with an employment record, a manager, and a departure date. AI agents have none of those. As autonomous principals proliferate across ente...
‘BioShocking’ Attack Tricks AI Browsers Into Stealing Credentials
Researchers show how context manipulation can cause agentic browsers to abandon safety guardrails and exfiltrate sensitive credentials. The post ‘BioShocking’ Attack Tricks AI Browsers Into Stealing C...
AI Agent Exploits Langflow RCE to Automate Database Ransomware Attack
Security firm Sysdig says it has found what it believes is the first ransomware attack run from start to finish by an AI agent. Its Threat Research Team calls the operator JADEPUFFER and says a large...
Apify Model Context Protocol (MCP) server: Actor MCP path authority injection leaks Apify token
## Actor MCP path authority injection leaks Apify token ### Summary `@apify/actors-mcp-server` version `0.10.7` builds Actor standby URLs by directly concatenating a trusted base URL with an attacke...
repomix: attach_packed_output can bypass file-read secret scanning for supported local files
# `attach_packed_output` can register arbitrary `.json/.txt/.md/.xml` files and bypass the MCP file-read safety check ## Summary Repomix's MCP server exposes a normal `file_system_read_file` tool th...
Cortex has Untrusted Project Bootstrap Code Execution via `CLAUDE_PROJECT_DIR`
## Untrusted Project Bootstrap Code Execution via `CLAUDE_PROJECT_DIR` ### Summary The Cortex MCP server (`neuro-cortex-memory`) treats the `CLAUDE_PROJECT_DIR` environment variable — automatically...
auth-fetch-mcp has SSRF Protection Bypass via IPv4-mapped IPv6 Loopback
## SSRF Protection Bypass via IPv4-mapped IPv6 Loopback ### Summary `auth-fetch-mcp` v3.0.1 implements SSRF protection in `assertSafeUrl()` (`src/security.ts`) to block requests to private and loopb...
CVE-2026-58446: Presenton before 0.8.8-beta bundles an MCP server that, on server/Docker deployments configured with session authenticat
Presenton before 0.8.8-beta bundles an MCP server that, on server/Docker deployments configured with session authentication (AUTH_USERNAME/AUTH_PASSWORD), is reachable unauthenticated at /mcp because...
CVE-2026-10564: IBM Langflow OSS 1.0.0 through 1.9.6 contains a Server-Side Request Forgery (SSRF). The legacy RSSReaderComponent in rss
IBM Langflow OSS 1.0.0 through 1.9.6 contains a Server-Side Request Forgery (SSRF). The legacy RSSReaderComponent in rss.py and SearXNG component in searxng.py make unvalidated HTTP requests to user-c...