Metal Mantra / AGENT INTELLIGENCEPublic evidence reportAUTOMATED SIGNAL. NOT CERTIFICATION.
PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2

qm.

Scanned repository says: Most agents are designed like personal assistants. You can make one work for a whole

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

15.3k starsMITpushed today

0community interest

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

AUTOMATED SIGNAL81/100BBBNot 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 / 887Partial eligible-file selection · not the entire repository
Recorded findings5Heuristic 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 / 887Partial selection
READMEReadRepository-authored information
MANIFESTS2LICENSE, package.json

Who it is for

  • Stated purpose · repository says · unreviewed

    Most agents are designed like personal assistants. You can make one work for a whole

    README.md:21
  • Stated purpose · repository says · unreviewed

    company, but it quickly gets complex. QM is designed for startups. Employees each get

    README.md:22
  • Stated purpose · repository says · unreviewed

    their own isolated workspace, and can also collaborate with the agent in channels, group messages, and projects.

    README.md:23

What it can do

  • Stated capability · repository says · unreviewed

    Personal and shared scopes. People customize the agent to be theirs, and still

    README.md:42
  • Stated capability · repository says · unreviewed

    work with it collaboratively in Slack channels and projects.

    README.md:43
  • Stated capability · repository says · unreviewed

    Slack and web. The same identity and configuration carries between Slack and the

    README.md:44

What adoption takes

  • Stated deployment · repository says · unreviewed

    Tell your coding agent of choice Let's deploy https://github.com/yc-software/qm. From here, it should follow the deployment guide in this repo.

    README.md:34
  • Stated prerequisite · manifest declares · unreviewed

    Manifest declares Node.js >=24.15.0 as a requirement.

    package.json:9
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on zod.

    package.json:110
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @anthropic-ai/claude-agent-sdk.

    package.json:71
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @anthropic-ai/tokenizer.

    package.json:72
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @aws-crypto/sha256-js.

    package.json:73
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @aws-sdk/client-ecs.

    package.json:74
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on @aws-sdk/client-s3.

    package.json:75

Limits and terms

  • Declared license · manifest declares · unreviewed

    Manifest declares MIT as its license.

    package.json:5

Observed technical context

TypeScript · 200 selected files

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

Read from commit fc54a60 at Oct 12, 2026, 4:49 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: 526 exact runtime versions from package-lock.json checked against OSV.dev on Oct 12, 2026; 0 with known advisories. Reachability is not checked.

5 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
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.

[domain not provided] · location unavailable
MAJOR

HTTPS not confirmed

TRUST002 · Entity trust

The stated website could not be reached over HTTPS, so Metal Mantra could not confirm it is a secure, working site.

SUGGESTED ACTION

Make the official website reachable over HTTPS for verification.

[domain not provided] · location unavailable
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.

[domain not provided] · 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.

[domain not provided] · location unavailable
03 / EVIDENCE & LIMITS

The boundary
is part of the result.

What was scanned
200 of 887 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: not confirmedPrivacy: 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

1 findings · 25% weight
82/10020.5 pts
02

Guardrails & loop control

0 findings · 25% weight
100/10025.0 pts
03

Schema & tooling

0 findings · 20% weight
100/10020.0 pts
04

Token & cost efficiency

0 findings · 15% weight
100/10015.0 pts
05

Entity trust

4 findings · 15% weight
0/1000.0 pts
Inspect the current standard
USER REPORTS

Did qm 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 81/100, not certified