mcp@3.13.0
VERIFIEDPublisher claims: "Detect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry npm (MCP server) · listed in the official MCP RegistryPublisher tuteliq · joined 1 days agoInstalls 0Last detonated 35 h ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-02 and scored it 88/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 2 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
2.1sprocessdependency install exit 1
2.3sprocessexec /usr/bin/timeout
2.3sprocessexited 1: Node.js v22.23.4
2.3sclaimedno tools/list reply (exit 1)
2.3sprocessscript backend runs setup only
Static findings
HIGH
Phishing urgency patternREADME.md:306 · Phishing urgency pattern — account threat languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Prompt injectionREADME.md:367 · Prompt injection — explicit attempt to bypass safety measuresFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01