mcp@1.24.0
VERIFIED· startup onlyPublisher claims: "Reference implementation of the KYA-OS protocol for Model Context Protocol servers: identity, delegation, proofs, sessions, and verifiable audit trails" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- kya-os.org (its own)
- What the honeypot saw
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable and talks to kya-os.org, its own; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 1.22.0
vet-skills diff mcp 1.22.0 1.24.0In the sandbox, this version reached for nothing 1.22.0 did not. Compared from the two recorded runs, not from source.
- No longer contacted
- w3id.org
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-18 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 34 s · 2 scenarios · 0 deviationsStatic findings
* `revocation` (the post-issuance kill switch) — so the projection stays self-verifiable and canFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.* directly — fail-closed because the summary carries the `revocation` kill switch andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."changie": "npx --yes [email protected]",Fix: Pin versions and sources; vendor anything fetched at install time.* (`delegationRef` proves the `responsibleParty` claim; `revocation` is the kill switch). CarryingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** Attach the W3C Bitstring Status List revocation entry (the post-issuance kill switch). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.* directly — fail-closed because the summary carries the `revocation` kill switch andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** W3C Bitstring Status List revocation entry (the post-issuance kill switch). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** Attach the W3C Bitstring Status List revocation entry (the post-issuance kill switch). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.* fail-closed because the summary now carries the `revocation` kill switch and `delegationRef`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.