- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This work curates agent skills, tool-use hooks, and other artifacts from publicly available sources, and proposes an approach for extracting common, useful set of capabilities/skills/hooks that can be used as safety validators on different agentic harnesses with various models. The empirical results seem convincing and broadly applicable across model choices, harnesses, and two benchmark choices. Also the safety-utility tradeoff study on Terminal bench shows that their approach retains utility.
Critical strengths
- The idea of curating existing skills and then extracting a common, useful subset that can achieve good empirical safety gains is interesting in general beyond just the domain of agent safety.
- The empirical gains are promising and broadly justify the promise of the proposed approach over a vanilla agent harness.
Critical weaknesses
- The idea of having tool-use hooks and skills for agent safety is well explored as noted by authors as they use these sources for curating their skills/capabilities. Yet they do not provide an experimental result that describes the benefit of doing this curation effort, which is their primary research contribution, as opposed to simply relying on a specific set of hand-chosen/standard set of skills, or even other approaches like using all possible sources with a searchable index on top of so that the agent can dynamically choose one without polluting the agent's context with unnecessary capabilities. Instead of discussing how their skills can reduce unsafe rates over a vanilla harness, it would be more beneficial if they discuss why their particular approach for curating these capabilities/interventions achieve better safety metrics over other approaches.
- The authors are positioning their work as a "library" but the main paper includes no discussion on how exactly their effort can be reused/plugged in to different agent harnesses. They demonstrate empirical results across different harnesses, and I agree that skill markdown files are reusable. But I am not very convinced especially about the tool-use hooks being re-usable across harnesses, because different agent harnesses can have different toolkits.
- I found the paper quite hard to follow: (a) the terms "capabilities" and "artifacts" should be formally/informally defined/explained via examples, (b) Section 4.5's methods like "Flat", "All-loaded" are also not explained very clearly.
Questions for authors
- The comparison of approaches based on total execution time is unfair on unsafe tasks because your interventions can prematurely terminate the task. A fair metric will be to use average additional overhead per turn instead of comparing full execution time. Or compare the total execution time on benign tasks after adding these safety interventions.
- While I understand that publicly available skills can be repetitive and you can consolidate them, is this effort really needed? Considering how strong the models you evaluate are (for e.g. GPT-5.6-SoL), I just wonder why we can't just let the model decide what skills and hooks are needed for a given task? I was also unable to understand how exactly a router is implemented in your pipeline? Is it just a skill document that describes what other interventions are available?
2 comments
Thanks for your response! I believe this draft needs significant revisions that must be addressed in a future submission. Hence I maintain my current score.
Response to Reviewer 6pf3 — Part 4
Q6: Necessity of consolidation and implementation of the Router.
The model already chooses its skills in our design, while the hooks must stay independent of the model. We first explain how the Router is implemented. We then answer the question about letting the model decide in three parts: whether the model can choose its skills, why it should not choose its hooks, and whether strong models still need hooks.
How the Router is implemented. The Router is a skill document (a meta-skill) with no trained component. The host makes it available to the agent, and the agent invokes it at the start of the task. The two tables below summarize its content.
Router card
safety-router-skillinvoke_skill(name="safety-router-skill", reference="detect-task-overreach")(Case 3, Appendix D)pass,warn, orblock, with the matched capability and a reasonblockpauses the workflow for human review. Awarnis logged and the workflow continues. If all checks returnpass, the workflow continues (Section 3.4)Phase map (archetypes with a model-side reference, from Table 12)
The Router therefore does more than list the available interventions. It also specifies when each reference should be read and how the check results are handled. We will add this card to Section 3.4.
Can the model decide which skills it needs? In our design, the model already makes this decision. It chooses which references to read, and the Router only tells it what is available in each phase. Consolidation changes what the model chooses from. Instead of 1,390 audited artifacts, the model chooses from 14 archetype references with clearly delimited scope.
Selecting less text also helps a strong model make safer decisions. For GPT-5.6 Sol, loading all curated references at the start gives a UAR of 17.27% on SABER and 33.70% on OpenAgentSafety. Reading only the references for the current phase gives 12.57% and 27.02% (Table 4). A small set of references with clear scope is what makes this selection practical.
Why the model does not decide which hooks to run. Hooks must not depend on the model, because they exist to catch the model's own mistakes. If the model chose its hooks, a wrong judgment would also switch off the check meant to catch it. Case 2 in Appendix D illustrates this. The post-tool hook removes live passwords read from
~/.pypircbefore the result reaches the model, whereas a model deciding whether to redact would have to read the passwords first. Hooks therefore run on every tool call, and the model cannot override a hook denial (Section 3.4).