Based on the RiskyPlugins AI security review of the observed evidence.
Analysis record
- Analysed
- 10 months ago 22 January 2026
- Version
- v0.0.58
- Detail
- Full list
Evidence ledger
Ranked by severity · findings with a source location link to the code viewer
YARA Rule Matches
9 rules| Severity | Rule | Hits | Files | Metadata |
|---|---|---|---|---|
| HIGH | postinstall system command System command execution detected | 20 | out/extension.jsout/extension-old.jsrules/openmemory-roo.md +17 more | Risky Plugins Authors FP 10% |
| HIGH | postinstall network communication Network communication detected | 12 | rules/openmemory.instructions.mdopenmemory.mdrules/openmemory-cline.md +9 more | Risky Plugins Authors FP 30% |
| HIGH | postinstall persistence mechanism Persistence mechanism detected | 11 | .cursor/rules/openmemory.mdcpackage.jsonopenmemory.md +8 more | Risky Plugins Authors FP 20% |
| HIGH | postinstall file manipulation File system manipulation detected | 12 | rules/openmemory.instructions.mdout/utils/fileOps.jsrules/openmemory-cline.md +9 more | Risky Plugins Authors FP 20% |
| HIGH | NoUseWeakRandom When software generates predictable values in a context requiring unpredictability, it may be possible for an attacker to guess the next value that will be generated, and use this guess to impersonate another user or access sensitive information. As the Math.random() function relies on a weak pseudorandom number generator, this function should not be used for security-critical applications or for protecting sensitive data. In such context, a cryptographically strong pseudorandom number generator (CSPRNG) should be used instead. For more information checkout the CWE-338 (https://cwe.mitre.org/data/definitions/338.html) advisory. | 1 | out/extension-old.js | FP 5% |
| HIGH | postinstall environment access Environment variable access detected | 3 | out/core/mcpConfigurator.d.tsout/handlers/uriHandler.d.tsout/core/configResolver.d.ts | Risky Plugins Authors FP 40% |
| HIGH | postinstall obfuscation Code obfuscation techniques detected | 9 | rules/openmemory-roo.mdrules/openmemory-qoder.mdrules/openmemory.mdc +6 more | Risky Plugins Authors FP 20% |
| HIGH | credential env files Environment configuration file path detected | 3 | out/utils/detection.jsout/extension-old.jsopenmemory.md | Risky Plugins Authors FP 10% |
| HIGH | postinstall crypto operations Cryptographic operations detected | 14 | rules/openmemory-roo.mdout/core/installer.jsrules/openmemory-kilocode.md +11 more | Risky Plugins Authors FP 30% |
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.
Finding Categories
YARA Rules Matched
9 rules(85 hits)AI Security Report
AI Security Review
Evidence context: threat category none; evidence quality strong.
The OpenMemory extension, developed by Mem0, is designed to provide memory for coding agents such as Cursor, Windsurf, Qoder, Trae, GitHub Copilot, Claude Code, VSCode, etc. The extension's filesystem and process access seem justified by its stated purpose, as it requires access to files and processes to function properly. For instance, the fileOps.js.map and fileOps.d.ts files suggest that the extension is handling file operations, which is consistent with its purpose. However, there are no credential-access findings targeting actual secrets, such as .env, .ssh, or cloud credentials. The strongest counterargument to the verdict is that the extension has a large number of findings, but upon closer examination, these findings are primarily related to metadata and code-smell, which are not indicative of malicious behavior. Specifically, the HASH-8cfbfb46d9694d7c and HASH-d64f5b827f5c4d65 findings are related to metadata and do not pose a security risk. Overall, the extension's behavior is consistent with its stated purpose, and there is no evidence of malicious intent.
Key Reasons
- justified filesystem and process access
- no credential-access findings targeting actual secrets
- code-smell and metadata findings are not indicative of malicious behavior
False Positive Considerations
- code-smell findings
- metadata findings
Reviewed 2026-05-23; recommended action: no action; model confidence 80%.
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