Metal Mantra / AGENT INTELLIGENCEPublic evidence reportAUTOMATED SIGNAL. NOT CERTIFICATION.
Metal Mantra
Run free scan
Metal Mantra
Run free scan

Public agent signals. Clear evidence boundaries.

PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2

mem0.

Scanned repository says: Long-term memory for AI Agents

Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.

Inspect GitHub source

67k starsApache-2.0pushed 3d ago

0community interest

Votes show community interest, not safety. They never change this score.

AUTOMATED SIGNAL46/100CCCNot security certification
START HERE

Critical findings need attention.

Critical finding · details withheld for 30 days

Inspect the findings
WHAT THIS DOES NOT ESTABLISH

Runtime safety, real-world agent capability, fitness for your use case or independent certification.

Scan scope200 / 695Partial eligible-file selection · not the entire repository
Recorded findings21Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
01 / KNOW THE REPOSITORY

What the source
actually tells us.

Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.

INSPECTED SOURCE200 / 695Partial selection
READMEReadRepository-authored information
MANIFESTS2LICENSE, pyproject.toml

Who it is for

  • Stated purpose · manifest declares · unreviewed

    Long-term memory for AI Agents

    pyproject.toml:8

What it can do

No explicit capability or integration was extracted; that does not mean none exists.

What adoption takes

  • Stated prerequisite · manifest declares · unreviewed

    Manifest declares Python >=3.10,<4.0 as a requirement.

    pyproject.toml:15
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on qdrant-client.

    pyproject.toml:17
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on pydantic.

    pyproject.toml:18
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on openai.

    pyproject.toml:19
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on httpx.

    pyproject.toml:20
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on posthog.

    pyproject.toml:21
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on pytz.

    pyproject.toml:22

Limits and terms

  • Declared license · manifest declares · unreviewed

    A license or copying file is present; its terms have not been reviewed.

    LICENSE:1

Observed technical context

TypeScript · 131 selected filesPython · 69 selected filesModel API reference · static onlyTool-calling reference · static only

These are references in selected source files, not proof that a feature works at runtime.

Read from commit b7ad69a at Oct 12, 2026, 5:15 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.

02 / FINDINGS FIRST

What needs
a closer look.

Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.

Dependencies: 315 exact runtime versions from poetry.lock checked against OSV.dev on Oct 12, 2026; 36 with known advisories. Reachability is not checked.

21 findings
CRITICAL

Critical finding · details withheld for 30 days

SEC001 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
CRITICAL

Critical finding · details withheld for 30 days

SEC001 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
CRITICAL

Critical finding · details withheld for 30 days

SEC002 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
MAJOR

Database query built from text

SEC009 · Security & privacy

A SQL statement is assembled by inserting values into the query text. If any of those values comes from a user or from model output, as in text-to-SQL agents, it can rewrite the query.

SUGGESTED ACTION

Pass values as bound parameters and allow-list identifiers such as table and column names.

integrations/antigravity-plugin/core/memory_core.py:971
MAJOR

Database query built from text

SEC009 · Security & privacy

A SQL statement is assembled by inserting values into the query text. If any of those values comes from a user or from model output, as in text-to-SQL agents, it can rewrite the query.

SUGGESTED ACTION

Pass values as bound parameters and allow-list identifiers such as table and column names.

integrations/claude-code-plugin/core/memory_core.py:971
MAJOR

LLM request without token ceiling

REL001 · Guardrails & loop control

A model request does not set a maximum output length. One unusual input can produce a very long, expensive response.

SUGGESTED ACTION

Set max_tokens or the provider's equivalent on each model call.

mem0-ts/src/oss/src/llms/anthropic.ts:83
MAJOR

LLM request without token ceiling

REL001 · Guardrails & loop control

A model request does not set a maximum output length. One unusual input can produce a very long, expensive response.

SUGGESTED ACTION

Set max_tokens or the provider's equivalent on each model call.

mem0-ts/src/oss/src/llms/azure.ts:29
MAJOR

LLM output without runtime schema

SCH001 · Schema & tooling

Model output is used without being checked against a schema. Unexpected or malformed output can break later steps or be trusted when it should not be.

SUGGESTED ACTION

Validate model output with Zod, JSON Schema, Pydantic or provider structured output.

mem0-ts/src/oss/src/llms/anthropic.ts:83
MAJOR

LLM output without runtime schema

SCH001 · Schema & tooling

Model output is used without being checked against a schema. Unexpected or malformed output can break later steps or be trusted when it should not be.

SUGGESTED ACTION

Validate model output with Zod, JSON Schema, Pydantic or provider structured output.

mem0-ts/src/oss/src/llms/azure.ts:62
MAJOR

Model call without fallback

EFF001 · Token & cost efficiency

A model call has no visible fallback. If the provider fails or is rate limited, the whole agent fails with it.

SUGGESTED ACTION

Configure a secondary model or explicit fallback path for provider failures.

mem0-ts/src/oss/src/llms/azure.ts:29
MAJOR

Domain ownership not verified

TRUST001 · Entity trust

Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.

SUGGESTED ACTION

Verify the domain using the Metal Mantra DNS TXT challenge.

mem0.ai · location unavailable
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

anyio 4.9.0 (PyPI) has known advisories: GHSA-5p39-cfhj-2xmp, GHSA-82r6-8w77-94w6, PYSEC-2026-4024, PYSEC-2026-4025 (highest severity critical). AnyIO: TLSStream IDNA 2003 host name encoding enables potential TLS certificate spoofing

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

poetry.lock:203
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

chromadb 1.5.9 (PyPI) has known advisories: GHSA-2wm9-hf6c-p5cr, GHSA-36p7-vc44-83pf, GHSA-f4j7-r4q5-qw2c, GHSA-xph7-9rjv-w5fr, PYSEC-2026-311 (highest severity critical). ChromaDB has a code injection vulnerability

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

poetry.lock:865
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

azure-core 1.35.0 (PyPI) has known advisories: GHSA-jm66-cg57-jjv5, PYSEC-2026-1208 (highest severity high). Azure Core is vulnerable to deserialization of untrusted data

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

poetry.lock:289
MINOR

Raw model text returned

SCH002 · Schema & tooling

The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.

SUGGESTED ACTION

Parse and validate the result before returning it.

mem0-ts/src/oss/src/llms/azure.ts:58
MINOR

Raw model text returned

SCH002 · Schema & tooling

The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.

SUGGESTED ACTION

Parse and validate the result before returning it.

mem0-ts/src/oss/src/llms/langchain.ts:161
MINOR

Privacy Policy link not confirmed

TRUST003 · Entity trust

No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.

SUGGESTED ACTION

Expose a clear Privacy Policy link on the official homepage.

mem0.ai · location unavailable
MINOR

Terms link not confirmed

TRUST004 · Entity trust

No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.

SUGGESTED ACTION

Expose a clear Terms link on the official homepage.

mem0.ai · location unavailable
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

aiohttp 3.13.5 (PyPI) has known advisories: GHSA-2fqr-mr3j-6wp8, GHSA-4fvr-rgm6-gqmc, GHSA-4m7w-qmgq-4wj5, GHSA-63hw-fmq6-xxg2, GHSA-9x8q-7h8h-wcw9 (highest severity moderate). aiohttp: HTTP/1 Pipelined Requests Queue Without Limit

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

poetry.lock:17
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

authlib 1.6.10 (PyPI) has known advisories: GHSA-jj8c-mmj3-mmgv, GHSA-r95x-qfjj-fjj2, PYSEC-2026-188, PYSEC-2026-25 (highest severity moderate). Authlib: Cross-site request forging when using cache

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

poetry.lock:260
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

filelock 3.18.0 (PyPI) has known advisories: GHSA-qmgc-5h2g-mvrw, GHSA-w853-jp5j-5j7f, PYSEC-2026-1374, PYSEC-2026-1375 (highest severity moderate). filelock Time-of-Check-Time-of-Use (TOCTOU) Symlink Vulnerability in SoftFileLock

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

poetry.lock:1750
03 / EVIDENCE & LIMITS

The boundary
is part of the result.

What was scanned
200 of 695 eligible files · Partial selection.
Supported static source patterns and domain checks; no runtime execution.
What remains unknown
Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
Source location
Links open the current repository HEAD. Source may have changed since this snapshot.
Something looks wrong?
Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
Entity trust · 15% of v0.2
Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.
DNS: unverifiedHTTPS: availablePrivacy: not confirmedTerms: not confirmed
04 / THE METHOD BEHIND THE NUMBER

Open the
calculation.

Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.

01

Security & privacy

11 findings · 25% weight
0/1000.0 pts
02

Guardrails & loop control

2 findings · 25% weight
76/10019.0 pts
03

Schema & tooling

4 findings · 20% weight
52/10010.4 pts
04

Token & cost efficiency

1 findings · 15% weight
86/10012.9 pts
05

Entity trust

3 findings · 15% weight
25/1003.8 pts
Inspect the current standard
USER REPORTS

Did mem0 work for people?

No user reports yet.

Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.

Sign in with GitHub to add a report

SHARE THE EVIDENCE

A signal.
Not a seal.

Share the full report so its scope and limits travel with the score.

Metal Mantra automated signal 46/100, not certified