loomkeep@0.1.0
VERIFIED· install onlyPublisher claims: "Enables AI agents and their human owners to browse, search (keyword, semantic, and hybrid), create, and revise a versioned personal knowledge base of Markdown documents, checkpoint summaries, and structured tasks. Access is OAuth-protected with separately grantable read and write scopes, and edits are history-tracked with conflict protection so concurrent clients don't overwrite each other." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
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
CLOUDFLARE_API_TOKENLOOMKEEP_TEST_SECRETMCP_AUTH_SECRETOAUTH_PROVIDERConfiguration, not credentials: CLOUDFLARE_ACCOUNT_ID, LOOMKEEP_BROWSER_PATH, LOOMKEEP_D1_ID, LOOMKEEP_KV_ID, LOOMKEEP_TEST_BASE, LOOMKEEP_VECTOR_DIMENSIONS, MCP_BASE_URL, VECTORIZE- Where it talks to
- no vendor host named in the codeAlso cloudflare.com, attacker.example, attacker.test — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names cloudflare.com, attacker.example, attacker.test as well as its own vendor. The guard injects CLOUDFLARE_API_TOKEN, LOOMKEEP_TEST_SECRET, MCP_AUTH_SECRET, OAUTH_PROVIDER only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 89/100 (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 · 0 s · 1 scenarios · 0 deviationsStatic findings
assert.equal(isAllowedImageSrc('file:///etc/passwd'),false);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert.equal(await session(request,{...env,MCP_AUTH_SECRET:otherSecret}),null);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert.equal(blockedImageNotice('https://user:[email protected]/a.png'),'［已封鎖的外部圖片：evil.example］');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.