pd-mcp-server@0.4.2
VERIFIED· install onlyPublisher claims: "Principles Disciple MCP Server — the single shared MCP server implementation for the three PD hosts (Codex, OpenClaw, WorkBuddy). Read-only pain recall through the Gate 3 Capability (SPEC-PD-MCP-GATE4-001)." 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 2026-11-13 and scored it 88/100 (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
…n. */ export declare const SUBMIT_TOOL_DESCRIPTION = "\u8BB0\u5F55\u4E00\u6761\"\u76F8\u5BF9\u951A\u70B9\u7684\u663E\u8457\u884C\u4E3A\u80CC\u79BB\"\uFF08Pain\uFF09\u3002\n\n\u8C03\u7528\u524D\u5FC5\u987B\u5B8C\u6210\u4E09\u4E…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.No other findings across 2,041 lines in 22 files.
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 @principles/pd-mcp-server@0.4.2 as of 20 h ago. This is the package itself, not its dependencies.