Unverified50% confidenceFactExact time
安全研究者将系统行动能力远超其安全判断能力的潜在风险称为能力越界（Capability Overhang）
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
The Security Risks of Running Unfamiliar Repos with Claude Code: How AI Agents Get Hijacked
bilibiliAIlazy俊7/7/2026
Related Claims
UnverifiedPoorly designed system prompts (such as those that overemphasize completing user tasks at all costs) may undermine the model's safety guardrails; the agent framework design, permission controls, and the security of the operated system collectively determine whether such incidents occur.70% similarUnverifiedOver-refusal strategies reduce risk but harm model utility, especially in scenarios such as professional development and security research that require touching sensitive boundaries.68% similarUnverified过度公开检测技术细节可能为恶意方提供规避蓝图67% similarUnverified过度对齐（Over-alignment）指模型安全护栏设置过于敏感，在完全合法的使用场景中也拒绝提供帮助的反向风险67% similarVerifiedExcessive safety fine-tuning can cause models to over-refuse, undermining their practical utility.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/391521API
curl https://kongchang.com/api/v1/knowledge/claims/391521MCP
get_claim(id=391521)