Unverified50% confidenceFactExact time
Indirect prompt injection is more dangerous than direct injection because agents often cannot distinguish between content to be processed and instructions to be followed.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrompt-level guardrails (constraining agent behavior solely through system prompts) are inherently fragile, and a more reliable direction is to enforce controls at the tool-call level.79% similarUnverifiedAgent behavior is highly non-deterministic, and the same input may produce completely different tool call chains across different runs.78% similarUnverified约束驱动提示（明确告知AI不应做什么）往往比目标驱动提示更能减少幻觉输出76% similarUnverifiedThe real risk of an agent lies not in the capabilities of the large language model behind it, but in which tools it is permitted to call.76% similarUnverifiedSelf-generated prompt injection is a security risk in which the injected instruction originates from the model itself rather than an external attacker.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/991786API
curl https://kongchang.com/api/v1/knowledge/claims/991786MCP
get_claim(id=991786)