Unverified50% confidenceDecision RuleExact time
When submitting a vulnerability finding, it is necessary to include the agent and model involved, the exact prompt or conversation sequence, what actually happened and what was expected to happen; reproducible steps are more valuable than screenshots.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedIn factor mining scenarios, candidate factors need to carry metadata such as statistical significance and data coverage to be passed to the backtesting agent for reasonable evaluation.72% similarUnverifiedAny scenario in which instructions and untrusted data share the same context (such as prompt injection, RAG, or agents) carries the risk that the model may follow information it was told to ignore.72% similarUnverifiedTo track and reproduce failures, each evaluation case needs to record the question, expected answer, retrieved document IDs and chunks, similarity scores, prompt and model configuration, generated answer, metric results, latency, and token usage, while avoiding recording keys or sensitive user data.71% similarUnverifiedAfter catching an exception, the error information should be returned to the large model verbatim rather than silently discarded, enabling the model to self-reflect, adjust its format, and retry, thereby improving agent robustness.71% similarUnverified工具调用使攻击面从让模型说错话升级为让模型做错事，危害从信息误导上升为实质性的数据访问和系统篡改70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1039683API
curl https://kongchang.com/api/v1/knowledge/claims/1039683MCP
get_claim(id=1039683)