Unverified50% confidenceFactExact time
The attackers fabricated job interview scenarios to induce targets to download AI tools containing malicious code, thereby stealing assets.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAttackers exploit AI tools already installed on developer machines as a foothold, and many attack payloads themselves exist as prompts in the form of Markdown files.73% similarUnverifiedAI coding tools have previously been exposed for secretly uploading user code.72% similarUnverifiedAI agents may come into contact with real people while interacting with scammers, raising legal disputes over whether their behavior constitutes entrapment; in most jurisdictions, the entrapment defense mainly applies to criminal proceedings and requires proving that the defendant had no original criminal intent.72% similarUnverifiedWhen an AI Agent is granted full file operation permissions, attackers can carry out prompt injection attacks by hiding malicious instructions within file content.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1132052API
curl https://kongchang.com/api/v1/knowledge/claims/1132052MCP
get_claim(id=1132052)