chat-recall@0.5.24
One memory across every AI coding tool — indexes Claude Code, Gemini CLI, Codex, OpenCode, Antigravity and Cursor sessions, redacts secrets, and exposes them to your agent over MCP.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package contains a concrete default-enabled remote update and persistence capability, but source inspection does not establish malicious intent or an unconsented install-time attack. Flag it as a warning for the risky server-controlled update channel.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Running a sync or watcher after login can reach auto-update; users must explicitly run hook, skill, or service commands for those changes.
Impact
A compromised or malicious configured server can cause code execution as the local user; explicit setup commands can persist the package watcher and modify AI-tool integrations.
Mechanism
Server-supplied archive download followed by global npm installation and service restart.
AI rationale
The package contains a concrete default-enabled remote update and persistence capability, but source inspection does not establish malicious intent or an unconsented install-time attack. Flag it as a warning for the risky server-controlled update channel.
Evidence
package.jsondist/auto-update.jsdist/cli.jsdist/telemetry.jsdist/service-installer.js~/.localchat-recall-watch.service
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- A running watcher can download a newer package archive from the configured server and install it globally.
- The update path verifies only a hash supplied by that same server, then invokes npm installation and restarts its service.
- Explicit commands install hooks and skills into several AI tool configuration areas.
- The package creates per-user background services when the user requests watcher service installation.
Evidence against
- package.json has no preinstall, install, or postinstall lifecycle hook.
- Network targets come from saved user login credentials; no fixed third-party collection host was found.
- Telemetry posts only to configured servers and rejects sensitive event fields before queuing.
- AI-tool configuration changes are exposed through named CLI commands rather than install-time execution.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
Source & flagged code
18 flaggeddist/self-restart.jsView file
40*/
L41: import { spawn } from 'child_process';
L42: import { readFileSync } from 'fs';
High
Child Process
Package source references child process execution.
dist/self-restart.jsView on unpkg · L40dist/watch.jsView file
1200for (var i = 0; i < flen; ) {
L1201: if (f.charCodeAt(i) === 37 && i + 1 < flen) {
L1202: lastPos = lastPos > -1 ? lastPos : 0;
...
L1435: fsWriteSync = () => fs.writeSync(this.fd, this._writingBuf);
L1436: fsWrite = () => fs.write(this.fd, this._writingBuf, this.release);
L1437: } else if (contentMode === void 0 || contentMode === kContentModeUtf8) {
...
L2000:
L2001: // ../../node_modules/thread-stream/package.json
L2002: var require_package = __commonJS({
...
L2045: type: "git",
L2046: url: "git+https://github.com/mcollina/thread-stream.git"
L2047: },
Critical
Credential Exfiltration
Source appears to send environment or credential material to an external endpoint.
dist/watch.jsView on unpkg · L120013185try {
L13186: const out2 = execFileSync2("powershell", [
L13187: "-NoProfile",
Findings
2 Critical12 High7 Medium5 Low
CriticalCredential Exfiltrationdist/watch.js
CriticalTrigger Reachable Dangerous Capabilitydist/cli.js
HighChild Processdist/self-restart.js
HighShelldist/watch.js
HighCredential Redirect Persistencedist/mcp.js
HighEntrypoint Foreign Package Code Overwritedist/mcp.js
HighCommand Output Exfiltrationdist/cli.js
HighEmbedded Payload Persistence Activationdist/auto-update.js
HighRemote Agent Bridgedist/mcp.js
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/cli.js
HighCross File Remote Execution Contextdist/watch.js
Affected versions and remediation
This report applies to chat-recall@0.5.24.
See all versions of chat-recall for other recorded verdicts.
- Review the evidence and your use of chat-recall@0.5.24 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.