llmesh-mcp@3.1.0
VERIFIEDPublisher claims: "Secure LLM Mesh over MCP — multi-LLM swarm + industrial IoT + privacy gateway" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher furuse-kazufumi · joined 0 days agoInstalls 42Last detonated 2 h ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 80/100 (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 · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/llmesh
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run
Static findings
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/CHANGELOG.md:756 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/REQUIREMENTS.md:1175 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/REQUIREMENTS.md:1083 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
AWS access key pattern detectedtests/test_firewall.py:228 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Bidirectional text override characters detectedtests/test_firewall.py:153 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Outbound HTTP to raw IP addressllmesh/rag/embedder.py:125 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
AWS access key pattern detectedtests/test_firewall.py:35 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Outbound HTTP to raw IP addresstests/test_discovery.py:164 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
AWS access key pattern detectedtests/test_firewall.py:168 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
URL using raw IP addressllmesh/rag/embedder.py:125 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Outbound HTTP to raw IP addressllmesh/rag/embedder.py:114 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07LOW
Prompt injectionREADME.md:120 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
URL using raw IP addresstests/test_discovery.py:164 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
GitHub token pattern detectedtests/test_firewall.py:39 · GitHub token pattern detected — possible hardcoded or harvested tokenFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03LOW
Prompt injectiondocs/SPECIFICATION.md:312 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Access to sensitive file pathstests/test_firewall.py:101 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
AWS access key pattern detectedtests/test_firewall.py:250 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
URL using raw IP addresstests/test_discovery.py:45 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07LOW
Prompt injection attemptdocs/SPECIFICATION.md:312 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Outbound HTTP to raw IP addresstests/test_discovery.py:67 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
URL using raw IP addresstests/test_discovery.py:67 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
URL using raw IP addressllmesh/rag/embedder.py:114 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Outbound HTTP to raw IP addresstests/test_discovery.py:45 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07LOW
Prompt injection attemptdocs/TROUBLESHOOTING.md:107 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01Cost to the agent
Instructions loaded
≈55 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.