Unverified50% confidenceSolutionExact time
Supply chain poisoning can contaminate upstream resources automatically consumed by Agents by embedding prompt injection instructions in the description fields of public npm/PyPI packages or by submitting Pull Requests containing malicious comments to open-source repositories.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEcosystems such as npm and PyPI have experienced supply chain attacks in which core packages were injected with malicious code or maintainer accounts were hijacked.73% similarUnverifiedDependency poisoning attackers can upload malicious packages with the same name as private packages but with higher version numbers to public package registries, luring build systems into automatically pulling them.69% similarUnverifiedAttackers can exfiltrate sensitive information out of the sandbox through legitimate outbound channels by embedding malicious code in dependency packages (supply chain attacks).67% similarUnverifiedSupply chain attacks plant malicious code indirectly by contaminating third-party libraries that a project depends on, rather than directly breaching the target project66% similarUnverifiedA malicious MCP Server can declare a legitimate tool name and embed prompt injection instructions in the description field; this type of attack is known as "Tool Poisoning."65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930847API
curl https://kongchang.com/api/v1/knowledge/claims/930847MCP
get_claim(id=930847)