Explore/agent app/Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents
T

Minghui Pan, Jiayuxuan Yang, Yuanyuan Yuan, Yu Jiang, Zhenpeng Chen/Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI AgentsUnknown

AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions. Yet LLMs often become substantially less safe when deployed as agents, and the source of this degradation remains poorly understood. In this paper, we identify schema-formatted tool specifications as a primary source of agent safety degradation and show, through white-box representation analysis, that they weaken the model's internal refusal signals and contribute to unsafe tool execution. Building on this finding, we propose SafeKeep, an inference-time safeguard that decouples safety judgment from tool execution: it assesses requests using flattened textual tool specifications while retaining the original schema-formatted specifications for execution. Across two representative benchmarks and four LLMs, including both white-box and black-box models, SafeKeep increases the average refusal rate for harmful requests from 23.8% to 70.6% and reduces the average attack success rate under observation-level prompt injection from 25.6% to 2.5%. It also outperforms existing safeguards and preserves task-handling capability. We release the code and data at https://github.com/snowcatsmoking/SafeKeep .

agent app
GitHubCompare
Refreshed 29d ago
OverviewActivity52wAlternativesDocs
Stars0
Forks0
HF Downloads—30d
Last commit—
Refreshed29d ago
Project healthUnknownNo activity data.
Production readinessResearch / EarlyBest for exploration and prototyping.
Risk notesUnknown licenseVerify license before production use.
AgentHub Score
55 / 100
Composite score from 6 signals. How we score →
Active project
55Score
Growth
40C
Activity
30C
Documentation
70C+
Maturity
45C
Community
42C
Production
58C
GitHub stars · 43 days observed0 not enough history
snapshots
Repository activity · 43 days observedReal snapshots from pushed_at
inactivepushed
2026-08-042026-09-17
Practical assessment
Should you use it?

✓ Best for

  • Research and experimentation
  • Prototype development
  • Learning agentic patterns

◎ Strengths

  • Active community
  • Open source
  • Well-documented API

✕ Not ideal for

  • Untested at scale without validation
  • Teams without AI/ML expertise

⚠ Watch-outs

  • Review changelog before updating
  • Verify license for commercial use
Technical details
What's inside
Language—
License—
Sourcearxiv
Open source✗ No
Commercial use—
Docs—
Demo—

AgentHub Score

55
Score 55/100
Below average

Alternatives

O
OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
0 · agent app
55
C
ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information
0 · agent app
55
O
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help
0 · agent app
55
U
Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents
0 · agent app
55Compare all →

Recent activity

Latest commit ——
Indexed by AgentHub crawler29d ago
Monitor for new releasesongoing