Unverified50% confidenceFactExact time
Reef Infra requires custom methods to explicitly declare a requests keyword argument; using the generic **kwargs will be directly rejected by the recipe at startup.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe root cause of prompt injection lies in the fact that LLM architecture encodes system prompts, user inputs, and externally retrieved content uniformly into the same continuous token sequence, making it impossible for the model to distinguish trusted instructions from untrusted data at the semantic level.53% similarUnverifiedOpenAI的Structured Outputs在token采样层面强制执行Schema约束，从根本上消除格式错误52% similarUnverifiedCustom instructions correspond at the underlying level to the system prompt mechanism of large language models; system prompts have the highest priority and are not visible to users.51% similarUnverifiedNot all models or platforms support custom tool calls, and in unsupported environments the DFS logic can degrade to a plain-text numbered list interaction.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973724API
curl https://kongchang.com/api/v1/knowledge/claims/973724MCP
get_claim(id=973724)