OpenMemory
The AI review rates the findings as likely false positive. The risk score (67/100) comes from stored counts that the review could not adjust. A new analysis will update it.
Analysis record
- Analysed
- 11 months ago 3 December 2025
- Version
- v0.0.58
- Artifact
- SHA256 4cf092c3…c8e84c
- Detail
- Counts only, rows expired
Detail for this analysis has expired
This analysis ran on 3 December 2025. 85 findings counted, and the counts are kept. The individual rows have aged out of storage. A new analysis restores them.
Detail for this analysis has expired
This analysis ran on 3 December 2025. 84 network indicators counted, and the counts are kept. The individual rows have aged out of storage. A new analysis restores them.
Publisher Evidence
Limited evidenceMem0
Publisher identity, store signals, distribution reach, and warning signals used for context. Treat this as supporting evidence, not a clean bill of health.
13 evidence rows available.
Detail for this analysis has expired
This analysis ran on 3 December 2025. 169 findings counted, and the counts are kept. The individual rows have aged out of storage. A new analysis restores them.
Stored counts by category
- 85
- Code patterns
- 85
- Malware signatures
- 84
- Network indicators
AI Security Report
AI Security Review
Evidence context: threat category none; evidence quality strong.
Filesystem and Process Access Justification
The OpenMemory extension provides memory functionality for coding agents (Cursor, Windsurf, GitHub Copilot, etc.), which legitimately requires reading source code files to build context for AI assistants. The evidence contains zero findings related to unauthorized process execution, postinstall payload execution, or suspicious child_process calls. The 85 code-smell findings (all marked high severity in the findings summary) are documented false positives per CVEQ guidelines—these rules fire on basic Node.js patterns and should never drive verdicts. No evidence of credential theft, workspace manipulation, or supply chain poisoning exists.
Credential Access Findings
The evidence contains zero secret findings. The single email IoC ([email removed] from [email removed]) is a contact email for the extension's own domain, not credential theft. The extension's legitimate API endpoints (https://api.openmemory.dev/mcp-stream' and https://app.openmemory.dev))) align with its stated purpose of memory management for coding agents. No findings reference .env files, .git/config, SSH keys, cloud credentials, or VS Code secret storage access.
Strongest Counterargument
The total finding count of 169 with 85 "high" severity code-smell findings and 84 medium-severity IoC findings could suggest elevated risk. However, the IoC findings are exclusively XIOC extractor garbage: source map files misidentified as domains (templates.js.map, detection.js.map, fileops.d.ts.map, gitignore.d.ts.map, fileops.js.map), official schema URLs (schemas.microsoft.com, schemas.openxmlformats.org, www.apache.org/licenses/), and the extension's own legitimate domains. Per CVEQ guidelines, IoC COUNT alone is meaningless—only specific non-generic suspicious domains matter. The zero malware signatures, zero obfuscation findings, zero secret findings, and zero tool-poisoning findings confirm this is a benign extension with noisy automated analysis.
The extension has 1,579 users on VS Code, indicating some adoption without widespread reports of malicious behavior. The findings pattern matches expected IDE extension artifacts: source maps, TypeScript definitions, and legitimate API calls to the publisher's infrastructure.
Key Reasons
- Zero malware signatures, obfuscation, or secret findings
- All IoCs are explainable as source maps, official schemas, or legitimate domains
- Code-smell findings are documented false positives that should not drive verdicts
- Extension purpose (memory for coding agents) justifies code reading behavior
False Positive Considerations
- XIOC extractor misidentifying source map files as domains
- Code-smell findings (85 total) are documented noise per CVEQ guidelines
- Official schema URLs flagged as IoCs (Microsoft, Apache, OpenXML)
- Extension's own legitimate domains flagged as suspicious
Reviewed 2026-04-29 · version 0.0.58; recommended action: suppress false positive; model confidence 85%.
Source Code Not Available
Source code is not available for this version of the extension.
About This Extension
Frequently Asked Questions
Similar Extensions
Related extensions from the same publisher or marketplace