Threat Library

IBM Langflow, an open-source visual builder for AI agent workflows, has a flaw in its ensure_fernet_key() function that produces weak cryptographic keys used to encrypt sensitive data such as credentials and secrets. This weakens the confidentiality guarantees of stored secrets, potentially allowing an attacker to decrypt or brute-force protected data if they gain access to the encrypted material. This is a genuine framework-level security issue affecting confidentiality of agent configuration/secrets rather than a direct agent-behavior exploit.

IBM Langflow OSS versions 1.0.0 through 1.10.3 use Python's non-cryptographic Mersenne Twister PRNG to derive Fernet encryption keys from short user secrets, making key generation deterministic and predictable. An attacker who can predict or brute-force the seed can regenerate the encryption key and decrypt stored API keys and authentication tokens used by the agent platform.

CVE-2026-66321 is a type confusion vulnerability in Microsoft Edge (Chromium-based) that allows an unauthorized remote attacker to execute arbitrary code, typically via a malicious or compromised web page. Exploitation requires a victim to interact with attacker-controlled content, but successful attacks can lead to full code execution within the browser context.

A vulnerability in Amazon Strands Agents Tools allows an authenticated user to manipulate the LLM into calling memory-management tools with a forged namespace parameter, letting them read, modify, or delete another tenant's stored memories. This is an insecure direct object reference (IDOR) bug affecting the mongodb_memory, elasticsearch_memory, and mem0_memory tool integrations before version 0.8.3. It poses a serious confidentiality and integrity risk in any multi-tenant deployment of these agent tools.

This is academic research demonstrating that LLM search agents can be manipulated by coordinating malicious content across multiple search results rather than relying on a single poisoned page. The 'Authority-Chain Hijack' technique creates a fake corroborating evidence trail across sources the agent cross-checks, achieving high attack success rates in controlled benchmarks (up to 71.4%/95.0% ASR with automated strategy refinement). No live exploit or in-the-wild activity is reported; this is a demonstrated vulnerability class with clear real-world implications for any agent trusting retrieved web content.

Researchers demonstrate LoginTrap, an indirect prompt injection technique that manipulates LLM-based web agents into believing login is a necessary step to complete a task, redirecting them to attacker-controlled login pages. This exploits the authentication boundary of web agents to potentially exfiltrate user credentials, achieving an 86% average success rate across multiple LLM backbones and agent architectures. This is a research disclosure, not an observed active exploit, but it demonstrates a credible and highly effective attack surface.

Poison Claude is an underground service advertising discounted, illegitimate access to Anthropic's Claude models (including Opus 4.8/4.7/4.6 and Sonnet 4.6), likely by reselling stolen or abused API credentials/accounts. The operator sits in the middle of every session, meaning all customer prompts, outputs, and potentially embedded secrets pass through an untrusted third party. This represents a significant confidentiality and data-exfiltration risk for any individual or organization using the service, including those integrating it into automated or agentic workflows.

A large-scale ClickFix campaign spanning over 250 front-end domains uses server-side browser fingerprinting to selectively serve fake software download lures to macOS users while hiding malicious content from crawlers and sandboxes. Microsoft Threat Intelligence has been tracking this infrastructure for weeks, noting the increased sophistication of its evasion techniques targeting Mac users specifically.

Threat actors exploited a SQL injection vulnerability to deploy the khunt post-exploitation toolkit directly within an Oracle database, using it as a foothold to breach the broader corporate network. This attack highlights database servers as an underexploited but high-value initial access vector, especially when they hold elevated privileges or trusted network connectivity.

A Canadian national pleaded guilty to participating in a large-scale data theft and extortion campaign targeting Snowflake cloud storage customers, affecting at least 165 organizations. The attackers used stolen or weak credentials—lacking multi-factor authentication—to access customer Snowflake instances, exfiltrate sensitive data, and extort victims for millions of dollars.

CISA has added CVE-2026-63077, a deserialization of untrusted data vulnerability in JetBrains TeamCity, to its Known Exploited Vulnerabilities catalog based on confirmed active exploitation. Under BOD 26-04, FCEB agencies must prioritize remediation of this vulnerability on publicly exposed assets, as it may grant attackers total control of affected systems post-exploitation. All organizations, including those outside federal scope, are strongly encouraged to remediate promptly given the severity of CI/CD compromise.

IBM Langflow's model provider validation function passes a user-supplied Ollama base URL directly into an outbound HTTP request without any scheme, host, or IP range validation. This allows an attacker to force the Langflow server to make requests to internal services, loopback addresses, or cloud metadata endpoints, potentially leaking credentials or enabling further internal network reconnaissance.

IBM Langflow OSS versions 1.0.0 through 1.10.3 execute LLM-generated Python code on the backend during Agentic Assistant validation, before a human approves it. An authenticated attacker can abuse this to run arbitrary code with backend privileges, potentially exfiltrating data or reaching internal network resources.

IBM Langflow, an open-source visual builder for AI agent/LLM workflows, contains an OS command injection flaw exploitable by an authenticated remote attacker to run arbitrary commands on the host. Because Langflow orchestrates agent pipelines and often has access to credentials, tools, and downstream systems, a compromise here can cascade into broader agent infrastructure. The CVSS 7.2 score reflects high impact but a requirement for authenticated access, moderating the overall risk.

IBM Langflow OSS versions 1.0.0 through 1.10.3 contain a vulnerability that allows a remote attacker to execute arbitrary code by exploiting improper validation of configuration parameters. Since Langflow is used to build and orchestrate AI agent workflows, a compromise here could give an attacker control over the host running agent pipelines. Organizations running affected versions should patch immediately given the high severity and remote, unauthenticated attack potential implied by the CVSS score.

A vulnerability in IBM Langflow OSS allows authenticated remote attackers to bypass localhost-only access controls and write arbitrary MCP server configurations into IDE config files on the host. This effectively lets an attacker plant malicious MCP servers that will be trusted and loaded by developer tooling, turning a web-facing Langflow instance into a foothold for compromising the developer's local environment.

IBM Langflow's implementation of the MCP resources/read request fails to sanitize file paths, allowing an attacker to use URL-encoded path traversal sequences to read arbitrary files on the server. This exposes sensitive data including other users' uploaded documents, the JWT signing secret, the SQLite database, and environment variables, which could enable full account takeover or further compromise.

IBM Langflow's handling of Docker-based MCP servers fails to properly filter dangerous volume-mount and device-mapping arguments, allowing an authenticated attacker to read, modify, or expose sensitive files on the host system. This is a high-severity flaw because it lets an already-authenticated but otherwise limited user escalate to host-level file access by abusing Langflow's MCP server tooling integration.

IBM Langflow OSS versions 1.0.0 through 1.10.3 contain a vulnerability where the 'command' field in MCP server configurations is not properly validated, allowing a remote authenticated attacker to execute arbitrary commands on the host system. This is a genuine and serious flaw since it turns a legitimate agent-tooling feature (MCP server setup) into a direct code execution path, though it does require prior authentication to exploit.

IBM Langflow versions 1.0.0 through 1.10.3 have an authentication bypass in the MCP composer endpoint that occurs when the default setting mcp_composer_enabled=true is combined with OAuth-based project authentication. This allows an attacker to circumvent intended access controls on MCP composer functionality, potentially gaining unauthorized access to project resources or agent workflows.