Agents
Finally, a paper testing whether hiding your agent skill files actually protects them. The short answer is no. That's concerning. Worth read…
Finally, a paper testing whether hiding your agent skill files actually protects them. The short answer is no. That's concerning. Worth reading if you sell access to a skill or share one across teams.
Finally, a paper testing whether hiding your agent skill files actually protects them. The short answer is no. That's concerning. Worth reading if you sell access to a skill or share one across teams. This new paper discusses more: Daydreaming reconstructs a hosted multi-file skill using only the ordinary tasks the service exists to perform. The victim is never asked to reveal the skill or grade a reconstruction, so disclosure filters have nothing to catch. At the weakest access level, where the attacker sees only the final response and returned files, it recovers 86.8 percent of the original skill's capability across 7 skills and 4 victim models. That is roughly 4x SigLeak, at a median of 32 victim calls per skill, with disclosure defenses enabled. Paper: https://arxiv.org/abs/2608.26733 Chat with Paper: https://academy.dair.ai/papers/hidden-agent-skills-can-be-stolen-through-normal-use-2608.26733
Related
- Finally a good paper testing if file-system based memory for LLM agents is worth it. First, what does this look like? Deployed agents keep l…
- Important read if you build with agent skills. Shared skill libraries are treated as a safe way for coding agents to reuse each other's work…
- New paper from Microsoft on Self-Evolving Agent Skills
Source: DAIR.AI (X) | 2026-08-29