webhound-mcp@0.5.2
VERIFIEDPublisher claims: "Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry npm (MCP server) · listed in the official MCP RegistryPublisher webhound · joined 1 days agoInstalls 0Last detonated 32 h ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-02 and scored it 91/100 (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 · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
Static findings
HIGH
Authorization escalation languageREADME.md:63 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Authorization escalation languageREADME.md:61 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
npx invocation of non-well-known packagebin/server.mjs:13 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06CRITICAL
Prompt injectionREADME.md:61 · 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:63 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01