chat-recall@0.5.19
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-aiNo concrete credential theft, foreign-package overwrite, or unconsented install-time agent-control mutation was confirmed. The automatic globally installed server-supplied update is a meaningful remote-code-execution trust boundary and warrants a warning.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
Run the watch daemon with saved credentials, or explicitly run chat-recall install-hooks.
Impact
A compromise of the configured update server could replace the global executable; hooks can run package scripts during Claude Code events.
Mechanism
Configured-server self-update and explicit Claude Code hook registration.
AI rationale
No concrete credential theft, foreign-package overwrite, or unconsented install-time agent-control mutation was confirmed. The automatic globally installed server-supplied update is a meaningful remote-code-execution trust boundary and warrants a warning.
Evidence
package.jsondist/auto-update.jsdist/watch.jsdist/cli.jsdist/sync-client.jshooks/chat_recall_save_hook.shhooks/chat_recall_resume_hook.shhooks/chat_recall_wakeup_hook.shhooks/chat_recall_escalate_hook.sh
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Unknown with low false-positive risk.
Evidence for warning
- The watch daemon automatically downloads, installs, and restarts an update from the configured logged-in server.
- The downloaded archive is globally installed with npm, creating a remote code execution trust boundary.
- An explicit install-hooks command writes chat-recall commands into Claude Code hook configuration.
Evidence against
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The update URL is derived from the configured server and checked against a server-provided SHA-256 value.
- Hook installation is an explicit user command, not install-time mutation.
- The sync client states that it redacts secrets before uploading session data.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
19 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
3 Critical12 High7 Medium5 Low
CriticalCredential Exfiltrationdist/watch.js
CriticalTrigger Reachable Dangerous Capabilitydist/cli.js
CriticalPrevious Version Dangerous Deltadist/auto-update.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
Affected versions and remediation
This report applies to chat-recall@0.5.19.
See all versions of chat-recall for other recorded verdicts.
- Review the evidence and your use of chat-recall@0.5.19 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.