instantclips-mcp@1.10.0
VERIFIEDPublisher claims: "Create branded vertical video ads from ecommerce product URLs or product photos." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry npm (MCP server) · listed in the official MCP RegistryPublisher instantclips · joined 6 days agoInstalls 0Last detonated 21 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 90/100 (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 · 3 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
2.5sprocessdependency install exit 1
2.7sprocessexec /usr/bin/timeout
2.7sprocessexited 1: Node.js v22.23.4
2.7sclaimedno tools/list reply (exit 1)
2.7sprocessscript backend runs setup only
Static findings
CRITICAL
Prompt injectionREADME.es.md:116 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionREADME.md:109 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionREADME.md:112 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionREADME.es.md:120 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionREADME.zh-CN.md:97 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionREADME.md:123 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01HIGH
Authorization escalation languageREADME.md:112 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Authorization escalation languageREADME.md:123 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Authorization escalation languageREADME.md:109 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Prompt injectionREADME.zh-CN.md:100 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01HIGH
Authorization escalation languageREADME.es.md:116 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Authorization escalation languageREADME.es.md:120 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Authorization escalation languageREADME.zh-CN.md:97 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Authorization escalation languageREADME.zh-CN.md:100 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01