INTEL_REPORT
arXiv — Cryptography & Security (cs.CR) · published 6/15/2026, 4:00:00 AM · TLP amber
Summary
Ingested excerpt (first ~500 chars of normalized text).
SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills arXiv:2606.14154v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly extend their capabilities at runtime by loading Agent Skills, which pair natural-language specifications (SKILL.md) with executable scripts and resources. Because a skill's behavior relies on both natural-language instructions and executable code, assessing its safety requires cross-m…
https://arxiv.org/abs/2606.14154
sha256:3fc0b8b14741642bcaf64333799a9c9d57638c8597ba9befda9c3057ed28892a
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.
| Type | Value | Link |
|---|---|---|
| domain | skill.md | Open → |
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.