kavach-mcp@0.1.11
VERIFIEDPublisher claims: "Security middleware for Model Context Protocol (MCP) that detects and blocks malicious tool calls" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher shivamnamdeo0101 · joined 0 days agoInstalls 49Last detonated 2 h ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-05 and scored it 84/100 (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
0.0sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
Static findings
LOW
Prompt injection attemptREADME.md:73 · 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.
AST01HIGH
Leet speak prompt injectionREADME.md:73 · Leet speak prompt injection — obfuscated 'override instructions'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01Cost to the agent
Instructions loaded
≈60 tok
1 file · 17 in bundle
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.