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...