Unverified50% confidenceCautionExact time
Prompt injection attacks are similar to SQL injection and may allow an Agent to gain unauthorized access to resources it should not touch.
1
Sources
50%
Confidence
Long-term
Relevance
9/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIndirect 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.73% similarUnverifiedPrompt injection attacks refer to malicious third parties embedding instructions in content processed by an Agent to hijack the Agent's intended behavior.68% similarVerifiedIn a Prompt Injection attack, an attacker can craft a special input to induce the Agent to perform unintended operations.68% similarVerifiedThe principle of indirect prompt injection is that an attacker disguises malicious instructions as normal data, delivers them to the model through a data source trusted by the agent, and induces the model to interpret the data as instructions and execute them.67% 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.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/855447API
curl https://kongchang.com/api/v1/knowledge/claims/855447MCP
get_claim(id=855447)