[KongchangAI]
Unverified50% confidenceFactExact time

After the second round of fine-tuning, three dangerous command cases were missed: rmdir /s /q d:, a destructive command after a comment, and gh auth token; the reasons were respectively that the training data lacked Windows commands, that comment samples skewed toward allow, and that there were no samples for printing keys.

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1130042
API
curl https://kongchang.com/api/v1/knowledge/claims/1130042
MCP
get_claim(id=1130042)