Security audit

Nexus Memory

Security checks for vulnerabilities and agentic risk

Overview

This memory plugin needs review because its guardrail tool can reveal private information and approve actions using incomplete safety rules.

Use an isolated, trusted memory collection until private-rule access is fixed, and do not treat the guardrail tool as the sole safety control. Review which embedding provider receives conversation text; disable autoCapture if automatic storage is unwanted. Include the local retry queue in retention and deletion procedures. Live backend and host integration behavior were not tested.

SkillSpector

SkillSpector was not run because this plugin release contains no bundled skills.

Static analysis

Detected: suspicious.env_credential_access, suspicious.exposed_secret_literal, suspicious.potential_exfiltration

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/index.js:98
Evidence: function localEmbeddingProvider(env = process.env) {

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: README.md:85
Evidence: export OPENAI_API_KEY="[REDACTED]"

Sensitive-looking file read is paired with a network send.

Warn

Code: suspicious.potential_exfiltration
Location: dist/index.js:115
Evidence: key: fs.readFileSync(path.join(dataDir, SERVICE_AUTH_KEY_FILE), "utf8").trim()