The paper introduces PACE, a Provenance-Aware Capability Enforcement system designed to secure tool-using large language model agents by mediating every tool call before execution. PACE employs path confinement to limit influence paths and verifies effects against authenticated authority, distinguishing certified execution contracts from evaluated configurations. Experiments on eight agent‑security benchmarks show that the evaluated configuration reduces attack success in most cases while maintaining near‑native utility.
arXiv:2609.37196v1 Announce Type: cross Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allow...
arXiv:2608.30041v1 Announce Type: cross Abstract: Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later pri...
arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.
arXiv:2606. 09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.
arXiv:2608. 12789v1 Announce Type: cross Abstract: Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey.
Tool-using LLM agents interact with the world through actions that persist state in artifacts (e. g.
arXiv:2609.14744v2 Announce Type: replace Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, bud...
arXiv:2609.22664v1 Announce Type: cross Abstract: Research on large language model agents for penetration testing is evaluated almost entirely by capability: whether the agent captures a flag or repr...
arXiv:2606. 04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval systems, memory modules, environments, and other agents.
AcquireBound is a runtime authorization framework that ensures AI agents can safely acquire and activate resources such as compute, credentials, and services. It quarantines acquired outputs, resolves their capabilities through authenticated evidence, and activates them only after verifying a manifest, provenance, and relational constraints. The system demonstrates strong safety properties, passing extensive benign and unsafe trace tests across multiple resource classes.
ClawSentry is an open‑source, framework‑agnostic security supervision gateway designed to protect autonomous large language model (LLM) agents from progressive risks that can arise at four points in the agent control loop: skill admission, invocation‑time intent, execution‑time effect, and post‑action consequence. It introduces a multi‑tier decision engine—deterministic L1, rule‑anchored L2, and read‑only L3—alongside a First‑Use Skill Package Review (FSPR) and an Agent Harness Protocol (AHP) that applies a single policy across multiple agent runtimes without modifying their internals. Evaluation on SkillInject and the SkillsSafety benchmark shows that ClawSentry significantly reduces contextual adversarial skill risk (ASR) while maintaining high task success rates (TSR).
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.