Who it is for
Electron workbench for the Kun runtime (HTTP/SSE)
package.json:6
PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2
kun.
Scanned repository says: Electron workbench for the Kun runtime (HTTP/SSE)
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 source0community interest
Votes show community interest, not safety. They never change this score.
73/100BBBNot security certification
Critical findings need attention.
Critical finding · details withheld for 30 days
Inspect the findingsRuntime safety, real-world agent capability, fitness for your use case or independent certification.
Scan scope200 / 5927Partial eligible-file selection · not the entire repository
Recorded findings8Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
What the source
actually tells us.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
200 / 5927Partial selection
ReadRepository-authored information
2LICENSE, package.json
What it can do
No explicit capability or integration was extracted; that does not mean none exists.
What adoption takes
Manifest declares Node.js >=22.19.0 as a requirement.
package.json:8Declares a dependency on @modelcontextprotocol/sdk.
package.json:125Declares a dependency on zod.
package.json:183Declares a dependency on @computer-use/nut-js.
package.json:120Declares a dependency on @google/design.md.
package.json:121Declares a dependency on @kun/extension-api.
package.json:122Declares a dependency on @kun/provider-catalog.
package.json:123
Limits and terms
Manifest declares PolyForm-Noncommercial-1.0.0 as its license.
package.json:280
Observed technical context
TypeScript · 200 selected filesTool-calling reference · static only
These are references in selected source files, not proof that a feature works at runtime.
Read from commit 8e16760 at Oct 12, 2026, 5:26 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.
02 / FINDINGS FIRSTWhat needs
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: 642 exact runtime versions from package-lock.json checked against OSV.dev on Oct 12, 2026; 2 with known advisories. Reachability is not checked.
8 findings
CRITICALCritical finding · details withheld for 30 days
Critical finding · details withheld for 30 days
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
CRITICALCritical finding · details withheld for 30 days
Critical finding · details withheld for 30 days
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
MAJORUntrusted data in privileged prompt
Untrusted data in privileged prompt
Text from a request appears inside a system or developer instruction. Instructions are the part of a prompt the model trusts most, so this is a common path for prompt injection.
Keep untrusted data outside system or developer instructions.
MAJORDatabase query built from text
Database query built from text
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.
Pass values as bound parameters and allow-list identifiers such as table and column names.
MAJORDomain ownership not verified
Domain ownership not verified
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
MAJORDependency with a high-severity advisory
Dependency with a high-severity advisory
xlsx 0.20.3 (npm) has known advisories: GHSA-4r6h-8v6p-xvw6, GHSA-5pgg-2g8v-p4x9 (highest severity high). Prototype Pollution in sheetJS
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MINORTerms link not confirmed
Terms link not confirmed
No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.
Expose a clear Terms link on the official homepage.
MINORDependency with a known advisory
Dependency with a known advisory
file-type 16.5.4 (npm) has a known advisory: GHSA-5v7r-6r5c-r473 (highest severity moderate). file-type affected by infinite loop in ASF parser on malformed input with zero-size sub-header
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
The boundary
is part of the result.
- What was scanned
- 200 of 5927 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: foundTerms: not confirmed
Open the
calculation.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
Security & privacy
26/100
Guardrails & loop control
100/100
Schema & tooling
100/100
Token & cost efficiency
100/100
Entity trust
40/100
Did kun 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.
SHARE THE EVIDENCEA signal.
A signal.
Not a seal.
Share the full report so its scope and limits travel with the score.
