afd-server@2.4.0
CAUTION· install onlyPublisher claims: "Server-side utilities for building AFD-compliant MCP servers with Zod validation" 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
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 2026-11-10 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
/** The validated input the token is bound to. */Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* createMcpServer({ transport: "http", ... });Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.// Only a message that declares JSON-RPC 2.0 can be a notification. The simple `/rpc` formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.throw new Error('createMcpServer: the stdio option was removed in 2.0. Use transport: "stdio", "http" or "auto" instead.');Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.* Unlike `createMcpServer()`, this does not create or start an HTTP server.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.* Unlike `createMcpServer()`, this does not create or start an HTTP server.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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 @lushly-dev/afd-server@2.4.0 as of 4d ago. This is the package itself, not its dependencies.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim lushly-dev: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.