registry / mcp-agents-memory / 0.9.19
mcp-agents-memory@0.9.19
Long-term memory for AI agents with provenance tracking
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe inspected entrypoint and required migration implement package-aligned memory capture and database maintenance. No concrete malicious behavior, install-hook abuse, or foreign agent configuration mutation was established.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Running the MCP server activates conversation capture; the migrate command runs database migrations.
Impact
The configured memory service stores conversation content; no malicious execution or credential diversion was established.
Mechanism
Conversation messages enter the configured database, while optional classification uses service-specific authentication. No unconsented agent control-surface writes were identified.
AI rationale
The inspected entrypoint and required migration implement package-aligned memory capture and database maintenance. No concrete malicious behavior, install-hook abuse, or foreign agent configuration mutation was established.
Network endpoints2
api.typesafe.ai/v1/systemoneapi.x.ai/v1
Decision evidence
public snapshotAI called this Clean at 90.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json declares no install hooks or runtime dependencies; prepare runs true.
- The flagged Claude projects location supports conversation reading, not agent configuration mutation.
- Captured messages are inserted into the memory database selected through caller configuration.
- Conversation capture starts with the MCP server and matches the package's memory functionality.
- The required librarian migration adds database columns inside a transaction.
- Optional Typesafe classification requires explicit enablement and authenticates to its fixed service endpoint.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsEvalFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
32 flaggedbuild/migrations/023_librarian_gate.jsView file
9195patternName = private_key_rsa
severity = critical
line = 9195
Critical
Critical Secret
Package contains a critical-looking secret pattern.
build/migrations/023_librarian_gate.jsView on unpkg · L91959195patternName = private_key_rsa
severity = critical
line = 9195
Critical
Secret Pattern
RSA private key in build/migrations/023_librarian_gate.js
build/migrations/023_librarian_gate.jsView on unpkg · L919512898var { readFile } = __require("fs");
L12899: var { execFile, spawn } = __require("child_process");
L12900: var { isParsedKey, parseKey } = require_keyParser();
High
Child Process
Package source references child process execution.
build/migrations/023_librarian_gate.jsView on unpkg · L12898Findings
29 Critical3 High3 Medium5 Low
CriticalCritical Secretbuild/migrations/023_librarian_gate.js
CriticalRemote Asset Decode Executebuild/index.js
CriticalRemote Response Code Executionbuild/index.js
CriticalTrigger Reachable Dangerous Capabilitybuild/index.js
CriticalSecret Patternbuild/migrations/023_librarian_gate.js
CriticalSecret Patternbuild/migrations/025_project_tag_alias_suggestions.js
CriticalSecret Patternbuild/migrations/014_drop_legacy_facts_constraints.js
CriticalSecret Patternbuild/migrations/008_schema_realignment.js
CriticalSecret Patternbuild/migrations/015_agent_provenance.js
CriticalSecret Patternbuild/migrations/028_raw_message.js
Critical
Affected versions and remediation
This report applies to mcp-agents-memory@0.9.19.
See all versions of mcp-agents-memory for other recorded verdicts.
- Review the evidence and your use of mcp-agents-memory@0.9.19 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.