Is @earendil-works/pi-agent-core safe?
- Node.js shell/command execution
- Node.js network egress
- MCP tool surface detected
@earendil-works/pi-agent-core is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 3 risky constructs are reported for review. It can: mcp tools detected, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
@earendil-works/pi-agent-core 0.99.1
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of @earendil-works/pi-agent-core's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (3)
The component can run operating-system commands or spawn processes.
import { spawn } from "node:child_process";const child = spawn("bash", ["-c", command], { cwd, stdio: ["ignore", "pipe", "pipe"] });Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.
The component makes outbound network requests.
const response = await fetch(`${options.proxyUrl}/api/stream`, {Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.
Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.
An MCP tool surface (manifest or tool definitions) was found.
this.registerTool(t, "open");
{"version":3,"file":"harness.js","sourceRoot":"","sources":["../../../src/harness/pico3/harness.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,eAAe,EAAE,MAAM,+BAA+B,CAAC;AAEhE,OAAO,EAAE,iBAAiB,EAAyB,MAAM,YAAY,CAAC;AACtE,OAAO,EAAE,aAAa,EAAE,QAAQ …Why it matters: Just context — review which tools it offers and their permissions.
Fix: Review the declared MCP tools and their permissions.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →