Towards a Unified Misuse Monitoring Benchmark

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluation...

How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation

Capture-the-Flag CTF benchmarks are widely used to assess the offensive security capabilities of autonomous language-model agents. Evaluations rely on shallow binary judgments or aggregate scores, overlooking the agent's trajectory to the flag. Consequently actual exploitation is conflated with...

EUVD-2003-1027

Malware in sbrugna...

EUVD-2023-23784

Malicious code in bioql PyPI...

The vulnerability of the UpdateTraceLevelSettings method in the software for managing and monitoring deleted objects in telemetry and telemechanics systems, allowing a hacker to circumvent security restrictions, read and write arbitrary files, and execute arbitrary code.

The vulnerability of the UpdateTraceLevelSettings method in software for managing and monitoring deleted objects in telemetry and telemechanics systems is related to the lack of protective measures for the SQL query structure. Exploiting this vulnerability allows a malicious actor to bypass...

CVE-2025-32863

A vulnerability has been identified in TeleControl Server Basic All versions V3.1.2.2. The affected application is vulnerable to SQL injection through the internally used 'UnlockTraceLevelSettings' method. This could allow an authenticated remote attacker to bypass authorization controls, to read...

Siemens TeleControl Server Basic SQL注入漏洞

Siemens TeleControl Server Basic is an industrial remote controller from Siemens, Germany. Siemens TeleControl Server Basic suffers from an SQL injection vulnerability that originates from an SQL injection in the UnlockTraceLevelSettings method, which can be exploited by an attacker to bypass...

Storefront - How to check the trace level of StoreFront diagnostics logs

This article describes how to check the trace level TraceLevel of the StoreFront diagnostics logs...

AWS SDK for Rust will log AWS credentials when TRACE-level logging is enabled for request sending

The awssigv4::SigningParams struct had a derived Debug implementation. When debug-formatted, it would include a user's AWS access key, AWS secret key, and security token in plaintext. When TRACE-level logging is enabled for an SDK, SigningParams is printed, thereby revealing those credentials to...

GHSA-MJV9-VP6W-3RC9 AWS SDK for Rust will log AWS credentials when TRACE-level logging is enabled for request sending

The awssigv4::SigningParams struct had a derived Debug implementation. When debug-formatted, it would include a user's AWS access key, AWS secret key, and security token in plaintext. When TRACE-level logging is enabled for an SDK, SigningParams is printed, thereby revealing those credentials to...

CVE-2023-30610

aws-sigv4 is a rust library for low level request signing in the aws cloud platform. The "awssigv4::SigningParams" struct had a derived "Debug" implementation. When debug-formatted, it would include a user's AWS access key, AWS secret key, and security token in plaintext. When TRACE-level logging...

Logs AWS credentials when TRACE-level logging is enabled

aws-sigv4 is a rust library for low level request signing in the aws cloud platform. The awssigv4::SigningParams struct had a derived Debug implementation. When debug-formatted, it would include a user's AWS access key, AWS secret key, and security token in plaintext. When TRACE-level logging is...

RUSTSEC-2023-0125 Logs AWS credentials when TRACE-level logging is enabled

aws-sigv4 is a rust library for low level request signing in the aws cloud platform. The awssigv4::SigningParams struct had a derived Debug implementation. When debug-formatted, it would include a user's AWS access key, AWS secret key, and security token in plaintext. When TRACE-level logging is...

CVE-2023-30610: Insertion of Sensitive Information into Log File

aws-sigv4 is a rust library for low level request signing in the aws cloud platform. The awssigv4::SigningParams struct had a derived Debug implementation. When debug-formatted, it would include a user's AWS access key, AWS secret key, and security token in plaintext. When TRACE-level logging is...

CVE-2023-1550

Insertion of Sensitive Information into log file vulnerability in NGINX Agent. NGINX Agent version 2.0 before 2.23.3 inserts sensitive information into a log file. An authenticated attacker with local access to read agent log files may gain access to private keys. This issue is only exposed when...

CVE-2023-1550

Insertion of Sensitive Information into log file vulnerability in NGINX Agent. NGINX Agent version 2.0 before 2.23.3 inserts sensitive information into a log file. An authenticated attacker with local access to read agent log files may gain access to private keys. This issue is only exposed when...

Design/Logic Flaw

Insertion of Sensitive Information into log file vulnerability in NGINX Agent. NGINX Agent version 2.0 before 2.23.3 inserts sensitive information into a log file. An authenticated attacker with local access to read agent log files may gain access to private keys. This issue is only exposed when...

CVE-2023-1550 NGINX Agent vulnerability CVE-2023-1550

Insertion of Sensitive Information into log file vulnerability in NGINX Agent. NGINX Agent version 2.0 before 2.23.3 inserts sensitive information into a log file. An authenticated attacker with local access to read agent log files may gain access to private keys. This issue is only exposed when...

CVE-2023-1550 NGINX Agent vulnerability CVE-2023-1550

Insertion of Sensitive Information into log file vulnerability in NGINX Agent. NGINX Agent version 2.0 before 2.23.3 inserts sensitive information into a log file. An authenticated attacker with local access to read agent log files may gain access to private keys. This issue is only exposed when...

CVE-2023-1550

Insertion of Sensitive Information into log file vulnerability in NGINX Agent. NGINX Agent version 2.0 before 2.23.3 inserts sensitive information into a log file. An authenticated attacker with local access to read agent log files may gain access to private keys. This issue is only exposed when...