» Tag
prompt-injection
38 postsDocker Desktop Bypass Lets AI Coding Agents Escape Their Sandboxes
Docker Desktop lets AI coding agents bypass strict sandboxes in Codex, Cursor, and Gemini CLI via a privileged socket and VirtioFS mount.
MCP's Confused Deputy Problem: Provenance Gaps, Injection, DNS Rebinding
MCP's confused deputy flaw explained: provenance gaps, prompt injection via fetch servers, DNS rebinding, and concrete detection rules.
Shut-down AI prompt firewall startup open-sources model and 13K attacks
A failed AI-firewall startup open-sources its two-stage prompt-injection detector, DeBERTa model, and 13,230 real jailbreak attempts.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comGhostCommit: the image-based exploit AI code reviewers miss
GhostCommit hides malicious instructions inside PNG images to bypass AI code reviewers like Cursor Bugbot and CodeRabbit undetected.
Cross-Channel Fragmentation Attacks Break MCP Tool-Calling Security
Researchers reveal cross-channel fragmentation attacks that bypass MCP security tools, exfiltrating data from LLMs across 15,000+ trials.
APPA Framework Cuts Prompt Injection Leaks in LLM Agents Near Zero
APPA is a new IFC framework that slashes prompt injection attack success in LLM agents to 0-7% while preserving most task utility.
Testing AI Agents: The Bug Hides in the Answer, Not the Trace
An AI agent passed eight straight safety tests, then silently broke one - a case study in why traces, not answers, reveal agent failures.
I Red-Teamed My Own LLM Security Gateway: Every Gap, Four Passes
An engineer red-teamed his own LLM security proxy across four passes, exposing secret-leak and prompt-injection gaps — including one still open in streaming.
Context Bombs: Using AI Safety Guardrails to Halt Rogue Agents
Tracebit research shows context bombs hidden in canaries can trigger AI safety guardrails, cutting autonomous attacker success rates by roughly 90%.
APC Framework Closes Authorization Gaps in Multi-Agent LLM Systems
A new authorization framework, APC, tracks delegated authority to block prompt-injection and unsafe action combinations in AI agents.