Unverified50% confidenceCautionExact time
Agents may execute destructive operations far beyond what was intended due to hallucination or prompt injection attacks.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn a Prompt Injection attack, an attacker can craft a special input to induce the Agent to perform unintended operations.76% similarUnverifiedHallucinations in agents directly translate into erroneous actions, including calling non-existent tools, fabricating file contents, and inventing error messages and then executing subsequent operations based on them.75% similarUnverifiedAgent链式调用多个技能时，若某个技能被恶意构造或存在漏洞，可能引发提示注入攻击（Prompt Injection）73% similarVerifiedPrompt injection attacks are a serious threat facing local AI Agents, as maliciously crafted content in files processed by the Agent may induce it to execute dangerous operations.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/898346API
curl https://kongchang.com/api/v1/knowledge/claims/898346MCP
get_claim(id=898346)