Security auditor for AI agent configurations. Scans Claude Code setups for vulnerabilities, misconfigs, and injection risks.
Drift inferred · capture-to-capture
- HIGH code analysis flagged committed secret ×2 in ecc-agentshield
transport stdio · http counts 0 tools · 0 res
· 0 prompts
permission surface via code analysis
no tools enumerated yet for this server.
prompt-surface
shipped agent-instruction files + hidden-content / dangerous-code findings —
quoted from the analyzed source
analyzed v1.4.0 · analyzer v17 · 1d ago
danger signals2
- committed secretOpenAI keypackage/dist/index.js:10369
sk-pro…(38 chars, redacted) - committed secretGitHub tokenpackage/dist/index.js:10384
ghp_re…(40 chars, redacted)
evidence-backed
findings quoted directly from the published source artifact — not inferred
filesystem 3
- fs package/dist/action.js :26
import { readFileSync as readFileSync2, writeFileSync, existsSync as existsSync2 } from "fs"; - fs package/dist/index.js :46
import { readFileSync, existsSync, readdirSync, statSync } from "fs"; - fs package/dist/miniclaw/index.js :41
import { mkdir, rm, stat, realpath, access } from "fs/promises";
shell / exec 2
- shell package/dist/index.js :9452
import { spawn } from "child_process"; - shell package/dist/miniclaw/index.js :197
pattern: /exec\s*\(|child_process|spawn\s*\(|system\s*\(/i,
network 2
- net package/dist/index.js :9641
detail: "JavaScript fetch() call to external URL", - net package/dist/miniclaw/index.js :592
import { createServer } from "http";
secrets 1
- secrets package/dist/index.js :15301
if (!process.env.ANTHROPIC_API_KEY) {
declared dependencies 13
- @anthropic-ai/sdk@^0.39.0
- chalk@^5.4.1
- commander@^13.1.0
- glob@^11.0.1
- yaml@^2.7.0
- zod@^3.24.2
- @types/node@^22.13.0
- @vitest/coverage-v8@^3.2.4
- eslint@^9.19.0
- tsup@^8.3.6
- tsx@^4.19.2
- typescript@^5.7.3
- vitest@^3.0.5