Unverified50% confidenceCautionExact time
Malicious or poorly crafted skills may leak API keys, sensitive data, or execute unexpected operations through an agent's tool-calling permissions.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
Unverified组合多个各自安全的技能模块可能产生意料之外的安全缺口，例如文件读取技能与网络通信技能结合可被利用实现数据外泄76% similarUnverifiedPermissions that appear harmless when held individually by an agent (such as reading files and calling an HTTP library) can enable data exfiltration when combined, which is the tool-combination emergence problem.75% similarUnverified在具备工具调用能力的 Agentic 系统中，一次成功的提示注入可能导致数据泄露、恶意代码执行甚至供应链攻击73% similarUnverifiedAfter agents gain tool-calling and external system access capabilities, the attack surface expands significantly, facing risks such as prompt injection, unauthorized operations, and data leakage73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958208API
curl https://kongchang.com/api/v1/knowledge/claims/958208MCP
get_claim(id=958208)