Environment variable access combined with network send.
Critical
- Code
- suspicious.env_credential_access
- Location
- dist/index.js:51
- Evidence
_dataDir = process.env.AMEM_DATA_DIR || path.join(os.homedir(), ".amem");
Security audit
Security checks across malware telemetry and agentic risk
This is a disclosed long-term memory plugin that stores conversation-derived facts and uses configured model services, so the main risk is privacy rather than hidden malicious behavior.
Install only if you want persistent agent memory. Keep hooks.allowConversationAccess disabled unless automatic memory capture is intended, use a local or trusted LLM endpoint for sensitive work, avoid discussing credentials or secrets while write-back is enabled, and scope Qdrant/review paths to locations you control.
SkillSpector was not run because this plugin release contains no bundled skills.
59/59 vendors flagged this plugin as clean.
Detected: suspicious.env_credential_access
_dataDir = process.env.AMEM_DATA_DIR || path.join(os.homedir(), ".amem");