safety security
The Agent Checks Where an Action Came From Before Committing It
PROVISO compares a proposed tool action with an alternative while keeping trusted and external observations distinct.
Summary
PROVISO compares a proposed tool action with an alternative while keeping trusted and external observations distinct.
Tool-using agents can repeat malicious or mistaken content supplied by external skills. PROVISO inserts a controller between proposal and execution, encoding trusted observations, external observations, the proposed action and an alternative in provenance-typed memory. Across four security tasks, the authors report that no baseline exceeded it on both security and utility; F1 improved by 13.84 points on SkillsBench and 7.07 on ToolSafe over the strongest baseline. The controller reduces measured risk but cannot make irreversible actions inherently safe.
Why it matters
PROVISO compares a proposed tool action with an alternative while keeping trusted and external observations distinct.
Limits and context
- The controller reduces measured risk but cannot make irreversible actions inherently safe.
Key claims
PROVISO compares a proposed tool action with an alternative while keeping trusted and external observations distinct.
Qualification: The controller reduces measured risk but cannot make irreversible actions inherently safe.
Evidence: source-2026-10-21-011
Sources
- arXiv preprint 2610.27115, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.