Unverified50% confidenceFactExact time
The open-source claude-code-security-review action explicitly states in its README that it has not been hardened against prompt injection.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedSynthID-Text在采样层面操作，不需要修改模型权重，且对文本质量的影响经实验验证几乎可忽略62% similarUnverifiedclaude.md differs from a general README in that its audience is the model rather than human readers, and it places more emphasis on executability and constraints.62% similarUnverifiedThe list of allowed tools and the stop-loss words should exist in code rather than in prompts, because prompts can be talked around while checks in code cannot.61% similarUnverified应始终以可读的纯文本标记源作为单一真相源，因其可被 Git 等版本控制系统高效跟踪差异，且不依赖特定软件、长期可读性高60% similarUnverifiedCLAUDE.md中可以明确写出禁止项，AI读取后不会朝那个方向生成代码60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1052135API
curl https://kongchang.com/api/v1/knowledge/claims/1052135MCP
get_claim(id=1052135)