Expired60% confidenceFactExact time
In testing, DeepSeek directly rejected prompts requesting the generation of code related to cyberattacks, explaining that the request exceeded the scope of its safety guidelines.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Testing DeepSeek's Safety Mechanisms: Multiple Jailbreak Attempts Successfully Blocked
bilibili枫叶边城6/15/2026
Related Claims
UnverifiedDeepSeek successfully intercepted multiple jailbreak attempts, rejecting sensitive requests multiple times under standard safety settings.76% similarUnverifiedWithout any prompt guidance, DeepSeek TUI autonomously performed path traversal, successfully discovered the hidden interface upload.jsp, and verified an arbitrary file upload vulnerability.66% similarPartially VerifiedIndirect prompt injection attacks plant hidden instructions within normal business data to induce Agents into executing unauthorized operations, representing a security risk at the semantic level rather than the code level.65% similarUnverified当加入会触发闭源模型安全分类器的生物/网络安全敏感请求时，DeepSeek V4输出质量突然大幅下降61% similarUnverifiedDirectly executing Skill code downloaded from the internet or autonomously generated by an agent in the host environment poses security risks, as it may contain dangerous operations such as deleting files, accessing sensitive directories, or launching network attacks.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/45501API
curl https://kongchang.com/api/v1/knowledge/claims/45501MCP
get_claim(id=45501)