Detonation LabsBehavioral security for the AI agent supply chain

DBPublic database

Every public detonation, with its evidence.

Each package we detonate publicly is listed here with its full report. Search before you install.

16
reports
1
malicious
2
suspicious
7
no malicious behavior

2 results · newest first

PackageVerdictTop findingConfidenceScanned
mcp-exploit-demogithub Suspicious Source code: hidden agent instructions in server.py Possible 25 Oct 2026 mcp-injection-experimentsgithub Suspicious Source code: hidden agent instructions in the server's own code Possible 25 Oct 2026

"No malicious behavior observed" reports observed behavior only. It does not prove a package is safe.