superclawd@0.1.71
Claude Code, supercharged — your team's standards, every session. The superclawd CLI loads your workspace's skills, agents, commands, workflows, and live directives into Claude Code as a plugin.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package has substantial capability to collect and remotely retain Claude session material, so it warrants a warning. Static inspection found no registry-install trigger, self-dependency chain, stealth persistence, or automatic broad project control-surface mutation that would justify a malicious verdict.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user logs in and launches Claude Code through the superclawd command.
Impact
Project and private-session content may leave the machine and become durable remote memories; remote directives can influence the launched agent session.
Mechanism
Claude hook-based transcript capture and remote memory synchronization.
AI rationale
The package has substantial capability to collect and remotely retain Claude session material, so it warrants a warning. Static inspection found no registry-install trigger, self-dependency chain, stealth persistence, or automatic broad project control-surface mutation that would justify a malicious verdict.
Evidence
dist/index.jsdist/hook-helper.mjs~/.superclawd/config.json~/.superclawd/sessions/<session>/plugin
Network endpoints2
mcp-api.superclawd.comapi.superclawd.com
Decision evidence
public snapshotAI called this Suspicious at 88.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- The CLI installs Claude Code hooks that read session transcripts and run detached background capture processes.
- Captured session content is sent to the SuperClawd API to create or update repository, private, and agent memories.
- The generated plugin injects remote workspace directives and MCP configuration into Claude Code sessions.
Evidence against
- package.json has no install, preinstall, or postinstall hook; publishing is the only lifecycle action.
- The risky behavior is reached through the explicit superclawd CLI, not package installation.
- The generated plugin is placed in a per-session SuperClawd directory rather than a consumer project's permanent Claude configuration.
Behavioral surface
ChildProcessEnvironmentVarsEvalFilesystemNetwork
HighEntropyStringsMinifiedUrlStrings
Source & flagged code
8 flaggeddist/index.jsView file
2Source sends the broad process environment to a literal external destination.
L2: import { createRequire as __cr } from 'module'; const require = __cr(import.meta.url);
L3: import{spawn as fn,spawnSync as zr,execSync as Qr}from"node:child_process";import{fileURLToPath as dn}from"node:url";import{existsSync as mn}from"node:fs";import{resolve as Zr,dirn...
L4: `,{mode:384});try{kn(ee,384)}catch{}}function Ye(){return A()?.preferences?.sk[redacted]===!0}function En(){return A()?.preferences?.notifications===!0}function Be(){return A()?...
L5: `)}catch{}}function ze(e,t,n=!1){Fe(Xe(e))||Cn(e,{notifications:n?!1:En(),...t?{workspace:t}:{}})}function Qe(){Fe(ee)||G({credentials:{keyId:"",secret:"",workspace:""},preferences...
L6: `)};function Rn(){try{switch(process.platform){case"darwin":return
Critical
Hardcoded Runtime Data Exfiltration
Source sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/index.jsView on unpkg · L22import { createRequire as __cr } from 'module'; const require = __cr(import.meta.url);
L3: import{spawn as fn,spawnSync as zr,execSync as Qr}from"node:child_process";import{fileURLToPath as dn}from"node:url";import{existsSync as mn}from"node:fs";import{resolve as Zr,dirn...
L4: `,{mode:384});try{kn(ee,384)}catch{}}function Ye(){return A()?.preferences?.sk[redacted]===!0}function En(){return A()?.preferences?.notifications===!0}function Be(){return A()?...
High
Findings
1 Critical6 High3 Medium7 Low
CriticalHardcoded Runtime Data Exfiltrationdist/index.js
HighChild Processdist/index.js
HighSame File Env Network Executiondist/index.js
HighCommand Output Exfiltrationdist/index.js
HighSandbox Evasion Gated Capabilitydist/index.js
HighTrigger Reachable Command Output Exfiltrationdist/index.js
HighSemantic Analysis Limiteddist/hook-helper.mjs#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowEvaldist/mcp-server.mjs
Affected versions and remediation
This report applies to superclawd@0.1.71.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.71 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.