registry / chat-recall / 0.5.4
chat-recall@0.5.4
Local-first memory for AI coding tools — indexes Claude Code / Gemini CLI / OpenCode / Codex sessions, exposes them over MCP, optionally syncs redacted history to a chat-recall server
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe scanner's claimed fixed credential gateway and foreign-package overwrite were not confirmed by source inspection. Runtime auto-installation across AI-tool skill surfaces and default-enabled remote self-update warrant a warning.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
User runs/configures chat-recall-mcp or its watcher after package installation.
Impact
Modifies AI-agent extension directories and may replace the package's global CLI with a server-provided update.
Mechanism
runtime-managed AI skill deployment and checksum-verified self-update
AI rationale
The scanner's claimed fixed credential gateway and foreign-package overwrite were not confirmed by source inspection. Runtime auto-installation across AI-tool skill surfaces and default-enabled remote self-update warrant a warning.
Evidence
package.jsondist/mcp.jsdist/install-skills.jsdist/auto-update.jsdist/sync-client.jsskills/chat-recall/SKILL.md~/.claude/skills/chat-recall-*~/.gemini/skills/chat-recall-*~/.codex/skills/chat-recall-*~/.local
Decision evidence
public snapshotAI called this Suspicious at 86.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- MCP startup automatically refreshes bundled skills into detected Claude, Gemini, Codex, and OpenCode directories.
- Skill installation deletes and replaces only directories marked chat-recall-managed.
- The watcher can download a same-origin update and globally install it when enabled.
Evidence against
- package.json has no preinstall, install, or postinstall lifecycle hook.
- Skill installation is package-owned, preserves unmarked user-owned skills, and is reachable through its CLI/MCP runtime rather than npm installation.
- Sync uses a configured server URL with bearer authentication; no fixed exfiltration endpoint or credential harvesting was confirmed.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
16 flaggeddist/self-restart.jsView file
40*/
L41: import { spawn } from 'child_process';
L42: import { statSync } from 'fs';
High
Child Process
Package source references child process execution.
dist/self-restart.jsView on unpkg · L40dist/watch.jsView file
11659try {
L11660: const out2 = execFileSync2("powershell", [
L11661: "-NoProfile",
High
1169Cross-file remote execution chain: dist/watch.js spawns dist/mcp.js; helper contains network access plus dynamic code execution.
L1169: for (var i = 0; i < flen; ) {
L1170: if (f.charCodeAt(i) === 37 && i + 1 < flen) {
L1171: lastPos = lastPos > -1 ? lastPos : 0;
...
L1404: fsWriteSync = () => fs.writeSync(this.fd, this._writingBuf);
L1405: fsWrite = () => fs.write(this.fd, this._writingBuf, this.release);
L1406: } else if (contentMode === void 0 || contentMode === kContentModeUtf8) {
...
L1969:
L1970: // ../../node_modules/thread-stream/package.json
L1971: var require_package = __commonJS({
...
L2014: type: "git",
L2015: url: "git+https://github.com/mcollina/thread-stream.git"
L2016: },
Findings
2 Critical10 High7 Medium5 Low
CriticalCredential Exfiltrationdist/cli.js
CriticalTrigger Reachable Dangerous Capabilitydist/cli.js
HighChild Processdist/self-restart.js
HighShelldist/watch.js
HighCredential Redirect Persistencedist/cli.js
HighEntrypoint Foreign Package Code Overwritedist/mcp.js
HighCommand Output Exfiltrationdist/mcp.js
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/cli.js
HighCross File Remote Execution Contextdist/watch.js
HighTrigger Reachable Credential Exfiltrationdist/cli.js
HighTrigger Reachable Persistencedist/cli.js
High
Affected versions and remediation
This report applies to chat-recall@0.5.4.
See all versions of chat-recall for other recorded verdicts.
- Review the evidence and your use of chat-recall@0.5.4 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.