MCP Atlassian: HTTP upload tools accept arbitrary server-local file

Ajar: Measuring Open Privilege in Agent Defenses

that boundary. Today these techniques are evaluated on agent-security benchmarks built around indirect prompt injection. Those benchmarks judge a defense by how far it brings the number of successful

@aborruso/ckan-mcp-server has SSRF via DNS-name → internal IP — incomplete fix

Universal Fractal Natural Language Decision Map: Real-Time Edge Triage Across Heterogeneous Domains

Acoustic Damping Filter grounded in token entropy and phonetic spectral density that insulates against prompt injections (0.0% empirical bypass; 95% Wilson CI: [0.0%, 30.8%]) while pruning escape iterations

ActGov: Governing LLM Agent Actions via Policy-Constrained Validation

attack configurations. It shows that ActGov consistently reduces the success rate of indirect prompt-injection attacks while preserving task utility, significantly outperforming existing defenses. These results demonstrate that ActGov

ActGov: Governing LLM Agent Actions via Policy-Constrained Validation

attack configurations. It shows that ActGov consistently reduces the success rate of indirect prompt-injection attacks while preserving task utility, significantly outperforming existing defenses. These results demonstrate that ActGov

Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models

models (p less than 0.01). We further show that steering creates a predictable prompt-injection attack surface whose vulnerability increases monotonically with steering magnitude. This finding is relevant to agent

CaMeLoT: CaMeL orchestrated with Temporal logic for static verification and liveness

data dependencies. We present CaMeLoT, a complement to CaMeL, an existing defence against prompt injection in tool-using LLM agents. CaMeLoT extends CaMeL by adding a static verification layer that

Trust propagation and structural containment in Multi-agent LLM pipelines

comprising a Supervisor, Researcher, Validator, and Executor. We evaluate shared-memory poisoning and indirect prompt injection through a forged approval embedded in a retrieved document. We compare the Validator

Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems

state had accumulated, we delivered three controlled stress events through ordinary interaction surfaces: indirect prompt injection, misinformation, and exposure of private agent memories. No evaluated world achieved full resilience across

Approval Integrity and Recovery in LLM Answer Publication

evidence-fingerprint changes expose asymmetric freshness enforcement between publication and recovery. A separate BIPIA prompt-injection experiment records zero target insertions among 266 valid editor outputs. External Hugging Face calibration

An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks

Agentic AI frameworks let a language model plan, keep memory

CodeWhale: image_analyze follows workspace symlinks, leaking external file bytes

Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond

interactions, while LLM-specific vulnerabilities can propagate across web applications, introducing attacks such as prompt injection. Securing modern web systems therefore requires understanding interactions between traditional and LLM-specific threats

Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents

availability, not epistemic standing: stored or retrieved material is not thereby supported. Untrusted inputs, prompt injections, and model inferences can therefore enter persistent state and later be presented as agent

Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents

rather than isolated errors. When a coding agent deletes a production database or a prompt injection spreads across agents, the incident raises questions of causality, authority, and non-repudiable third

Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems

hash of each released output; this records released bytes but does not prevent prompt injection. Ancestry evidence records edge authorization. Under a unified threat model, we compare a signed linked

Zero-Knowledge Predicate Proofs Between AI Agents: A Measured, Cross-Protocol Gateway and the Source-Integrity Gap

policy. The first over-shares; the second is unverifiable and is exactly the channel prompt injection attacks. Prevailing responses emphasise identity, visibility, and post-hoc detection, and recent proposals

Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection

Large language model agents place outputs from external skills into

mcp-shell — Security Disabled by Default in Bare-Binary Deploy