AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents

Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion AgentBench or security robustness AgentDojo, ASB, rather than the complete pipeline of planning, tool selection, tool execution, memory and reasoning. Failures can occur at any stage, yet existing...

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills

LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, but because the skill it invoked broke its own declared safety rules. We call these specification violations: benign inputs cause a skill to breach...

Clario: Multiple Information Disclosure with Go PPROF on api-ne.mackeeper.com

Summary Multiple Information Disclosure with Go PPROF on api-ne.mackeeper.com. Steps To Reproduce Go to: https://api-ne.mackeeper.com/debug/pprof/ You will see these links: - allocs: A sampling of all past memory allocations - block: Stack traces that led to blocking on synchronization primitives...

FreeBSD : sudo -- arbitrary command execution (1b725079-9ef6-11da-b410-000e0c2e438a)

Tavis Ormandy reports : The bash shell uses the value of the PS4 environment variable after expansion as a prefix for commands run in execution trace mode. Execution trace mode xtrace is normally set via bash's -x command line option or interactively by running 'set -o xtrace'. However, it may al...

Sendmail 8.118.12 Debugger - Arbitrary Code Execution (2)

Sendmail 8.118.12 Debugger - Arbitrary Code Execution 2 // source: https://www.securityfocus.com/bid/3163/info An input validation error exists in Sendmail's debugging functionality. The problem is the result of the use of signed integers in the program's tTflag function, which is responsible for...