INTEL_REPORT
arXiv — Cryptography & Security (cs.CR) · published 6/18/2026, 4:00:00 AM · TLP amber
Summary
Ingested excerpt (first ~500 chars of normalized text).
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents arXiv:2606.18356v1 Announce Type: new Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell…
https://arxiv.org/abs/2606.18356
sha256:150ed2953cc5d937302c4effda1cacec52e7b1d471ba903d04ca5ffc3b872f05
What we pulled out
Deterministic extractor (IOC + allowlisted tokens + ATT&CK IDs present in DB).
Indicators
Linked with report → mentions → indicator. Values open the indicator workspace.
Malware families
Allowlist token matches only.
Threat actors mentioned
Allowlist mentions — not a formal attribution verdict.
ATT&CK techniques
MITRE IDs referenced in text and present in local technique table.
CONTINUE INVESTIGATION
High-signal pivots without leaving the thread you started in search.
Browse the report corpus.
Neighborhood from the first linked indicator.