kapibala-mcp@0.1.2
VERIFIED· install onlyPublisher claims: "Model Context Protocol (MCP) client ecosystem adapter for Kapibala" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 0.0.10
vet-skills diff kapibala-mcp 0.0.10 0.1.2In the sandbox, this version reached for nothing 0.0.10 did not. Compared from the two recorded runs, not from source.
0.0.10 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
description: "\u6267\u884C MCP \u63D0\u793A\u8BCD\u6A21\u677F\u4EFB\u52A1",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.description: "\u67E5\u770B MCP \u670D\u52A1\u72B6\u6001\u3001\u5DF2\u6CE8\u518C\u5DE5\u5177\u6216\u91CD\u8FDE/\u5F00\u5173\u5F53\u524D\u4F1A\u8BDD\u670D\u52A1",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.description: "\u641C\u7D22 MCP \u63D0\u793A\u8BCD\u6A21\u677F\u4E0E\u53C2\u6570",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…mptArgument, type McpPromptDefinition, McpPromptRegistry, type McpProtocolMode, McpServerManager, type McpServerStatus, type McpServersInput, type McpStartupResult, type OmittedMcpTool, PLATFORM_BASE_ENV_WHITELIST, type PreparePromptTaskOp…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.description: "\u67E5\u770B MCP \u670D\u52A1\u72B6\u6001\u3001\u5DF2\u6CE8\u518C\u5DE5\u5177\u6216\u91CD\u8FDE/\u5F00\u5173\u5F53\u524D\u4F1A\u8BDD\u670D\u52A1",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.description: "\u641C\u7D22 MCP \u63D0\u793A\u8BCD\u6A21\u677F\u4E0E\u53C2\u6570",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.description: "\u6267\u884C MCP \u63D0\u793A\u8BCD\u6A21\u677F\u4EFB\u52A1",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for @kiturone/kapibala-mcp@0.1.2 as of 40 min ago. This is the package itself, not its dependencies.