Unverified60% confidenceFactExact time
Prompt injection attacks refer to malicious third parties embedding instructions in content processed by an Agent to hijack the Agent's intended behavior.
2
Sources
60%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
VerifiedIn a Prompt Injection attack, an attacker can craft a special input to induce the Agent to perform unintended operations.81% similarUnverifiedGoal hijacking is a specific manifestation of prompt injection, in which the attacker overrides the Agent's original goal through injected content so that it performs other tasks.79% similarVerifiedIndirect prompt injection refers to attack instructions hidden in external web pages, documents, or API responses accessed by an agent, where the malicious instructions are activated when the agent retrieves and injects them into the context.77% 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.74% similarVerifiedPrompt injection is a novel and unique attack vector targeting operational agents; malicious web pages can inject instructions into an agent via visual elements or hidden text, and how to distinguish real instructions from forged ones remains an open problem that has not been fully solved.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/556544API
curl https://kongchang.com/api/v1/knowledge/claims/556544MCP
get_claim(id=556544)