registry / mcp-agents-memory / 0.9.32
mcp-agents-memory@0.9.32
Long-term memory for AI agents with provenance tracking
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe manifest's prepare hook is inert. The only concerning external flow found is an explicitly enabled tagging feature that sends the memory text it processes to the Typesafe endpoint using a Typesafe API key; this matches the package feature and does not establish malicious behavior.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
The tagging flow calls the judge only when `JEV_ENABLED=true`; a usable Typesafe API key is also required.
Impact
The service processes memory text for tag selection. The inspected flow does not show collection of unrelated credentials or files.
Mechanism
Sends the memory message, role, agent platform and model, plus candidate tags, to `https://api.typesafe.ai/v1/systemone` using the Typesafe key as a bearer token.
AI rationale
The manifest's prepare hook is inert. The only concerning external flow found is an explicitly enabled tagging feature that sends the memory text it processes to the Typesafe endpoint using a Typesafe API key; this matches the package feature and does not establish malicious behavior.
Evidence
/home/admin_3alab/.config/typesafe/api_key
Network endpoints1
api.typesafe.ai/v1/systemone
Decision evidence
public snapshotAI called this Clean at 87.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The package's prepare script is `true`; the manifest shows no install-time action.
- The Jev judge runs only when `JEV_ENABLED` is exactly `true`, and its key comes from `TYPESAFE_API_KEY` or a Typesafe key file.
- The judge sends the memory message and tagging context to the Typesafe endpoint for project-tag selection.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsEvalFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
35 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
31 Critical3 High3 Medium6 Low
CriticalCritical Secretbuild/migrations/023_librarian_gate.js
CriticalRemote Asset Decode Executebuild/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/032_project_hint_venues.js
CriticalSecret Patternbuild/migrations/015_agent_provenance.js
CriticalSecret Patternbuild/migrations/028_raw_message.js
Affected versions and remediation
This report applies to mcp-agents-memory@0.9.32.
See all versions of mcp-agents-memory for other recorded verdicts.
- Review the evidence and your use of mcp-agents-memory@0.9.32 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.