Skill-Inject on prompt injection in agent skill files accepted at NeurIPS 2026, 80+ citations
maksym_andr · x · 2026-09-25
The paper Skill-Inject has been accepted at NeurIPS 2026. It studies prompt injection attacks embedded in agent skill files, and the poster notes it has already accumulated 80+ citations, calling skill-file injection "a big deal."
The topic is timely for the agent ecosystem: skills/MCP-style mechanisms let agents load external instruction files, and malicious injections there can hijack agent behavior — an attack surface AI security researchers are watching closely.
Related event: Skill-Inject Paper on Agent Skill Prompt Injection Accepted at NeurIPS 2026(2 posts)→
More from Safety
- Defending METR: public data can't second-guess its AI speedup findings — peterwildeford · 2026-11-11
- Australia's review of an OpenAI agent's unauthorized Medicare access exposes the agent accountability problem — cmb24k · 2026-11-11
- Adversarial RL envs for backdoor insertion vs. detection: where does it converge? — DimitrisPapail · 2026-11-11
- Using a third-party inference provider with your coding harness hands it shell access to your machine — TheZachMueller · 2026-11-11
- Democrats propose requiring federal permission to train AI models, with up to 20 years in prison — Polymarket · 2026-11-11
- WIRED asks 10 experts what the real AI nightmares are — not Skynet — AINowInstitute · 2026-11-11