Skills/Glama/kebivo

kebivo@0.3.0

CAUTION· install only

Publisher claims: "An MCP server that lets AI agents report unanswered questions and submit knowledge corrections to a self-hosted feedback endpoint. Reports are grouped, deduplicated, and routed to documentation owners through an admin inbox, email, or signed webhooks." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher ocnai · publishing for 0 daysInstalls 0Last detonated 8 h ago
What would fix thisWatchDispute verdict

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: Caution 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
KEBIVO_BURST_TOKENKEBIVO_TOKENMCP_CORRECTION_TOKENMCP_GAP_TOKENMCP_TOKENSECRET_KEYUPGRADE_PASSWORDConfiguration, not credentials: E2E_CHROMIUM_PATH, ENCRYPTION_KEY, EXPECTED_EVENT_ID, FAIL_FIRST, HOLD_SECONDS, KEBIVO_URL, MCP_IDEMPOTENCY_KEY, MCP_MARKER, MCP_PROJECT_ID, MCP_URL, SAMPLE_IDEMPOTENCY_KEY, SMOKE_API, SMOKE_COOKIE_JAR, SMOKE_CSRF, SMOKE_DELIVERED_CANARY, SMOKE_DELIVERED_ID, SMOKE_EVENT_ID, SMOKE_EXPECTED_CALLS, SMOKE_FAIL_FIRST, SMOKE_HOLD_SECONDS, SMOKE_ORIGIN, SMOKE_RETRY_CANARY, SMOKE_RETRY_ID, SMOKE_UI_ORIGIN, UPGRADE_COLUMNS, UPGRADE_STATE, UPGRADE_URL
Where it talks to
no vendor host named in the codeAlso example.org, slack.com, example.test, azure.example, astral.sh, unlisted.invalid — 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 example.org, slack.com, example.test, azure.example, astral.sh, unlisted.invalid as well as its own vendor. The guard injects KEBIVO_BURST_TOKEN, KEBIVO_TOKEN, MCP_CORRECTION_TOKEN, MCP_GAP_TOKEN, MCP_TOKEN, SECRET_KEY, UPGRADE_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 2026-11-14 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; URL to the cloud instance metadata address. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsfrontend/src/Settings.tsx:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…<p className="subtle">Read-only. Change these values in the server environment (.env) and restart.</p></div></div><SettingsNav active="general" navigate={navigate}/…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/e2e-ui.sh:60 · npx invocation of non-well-known package — may execute untrusted codenpx playwright test demo.spec.tsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/e2e-ui.sh:9 · npx invocation of non-well-known package — may execute untrusted code# bootstraps an admin, runs `npx playwright test` on the host against theFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsfrontend/src/Settings.tsx:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…/div>)}</dl><p className="subtle">To change a period, set the variable in <code>.env</code> and restart. <code>0</code> turns that class off.</p> {!allOff&&…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
URL to the cloud instance metadata addressscripts/container-phase4-smoke.py:71 · URL to the cloud instance metadata address — reads the VM's credentials"config": {"url": "http://169.254.169.254/secret-canary-path", "signing": False},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)frontend/src/main.tsx:351 · MCP server using network transport (SSE/HTTP) — data sent over networkconst config = JSON.stringify({ mcpServers: { kebivo: { type: 'http', url: endpoint, headers: { Authorization: 'Bearer <PROJECT_TOKEN>' } } } }, null, 2);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Slack webhook URLfrontend/src/Destinations.tsx:626 · Slack webhook URL — data will be sent to Slack: "https://hooks.slack.com/services/..."Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/container-smoke.sh:326 · Process kill command — agent can terminate processes"${compose[@]}" kill -s KILL app >/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsfrontend/src/app.test.tsx:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(init?.credentials).toBe('same-origin');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
URL to the cloud instance metadata addressscripts/fake_llm_server.py:121 · URL to the cloud instance metadata address — reads the VM's credentialsself.send_header("Location", "http://169.254.169.254/latest/meta-data")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)frontend/src/integrationSnippets.ts:57 · MCP server using network transport (SSE/HTTP) — data sent over network{ mcpServers: { kebivo: { type: 'http', url: `${origin}/mcp`, headers: { Authorization: `Bearer ${TOKEN_PLACEHOLDER}` } } } },Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Slack webhook URLfrontend/src/Destinations.test.tsx:185 · Slack webhook URL — data will be sent to Slack"https://hooks.slack.com/services/T123/B456/secret",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Slack webhook URLfrontend/src/Destinations.test.tsx:166 · Slack webhook URL — data will be sent to Slack"https://hooks.slack.com/services/T123/B456/secret";Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)frontend/src/app.test.tsx:196 · MCP server using network transport (SSE/HTTP) — data sent over networkexpect(JSON.parse(config).mcpServers.kebivo.type).toBe('http');Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagescripts/e2e-ui.sh:57 · npx invocation of non-well-known package — may execute untrusted codenpx playwright test screenshots.spec.tsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Slack webhook URLfrontend/src/Destinations.test.tsx:181 · Slack webhook URL — data will be sent to Slacksecrets: { url: "https://hooks.slack.com/services/T123/B456/secret" },Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/e2e-ui.sh:62 · npx invocation of non-well-known package — may execute untrusted codenpx playwright testFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Image alt text carrying instructionsREADME.md:70 · Image alt text carrying instructionsOrdered routing rules, the fallback destination and the dry-run simulatorFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Image alt text carrying instructionsREADME.md:68 · Image alt text carrying instructionsProject page with the REST and MCP connection snippets (cURL tab)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/container-phase5-smoke.py:280 · Python subprocess execution detectedcheck = subprocess.run(["python", "-m", "kebivo.cli", "check-groups"], capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/e2e.sh:68 · Process kill command — agent can terminate processes"${compose[@]}" kill -s KILL app >/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsfrontend/src/app.test.tsx:173 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(requests.every(({url,init})=>url.startsWith('/api/v1/')&&init?.credentials==='same-origin'&&!new Headers(init?.headers).has('Authorization'))).toBe(true);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/container-phase5-smoke.py:272 · Python subprocess execution detectedsubprocess.run(["python", "-m", "kebivo.cli", "check-groups"], capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈30 tok
1 file · 81 in bundle

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.

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. URL to the cloud instance metadata address≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim ocnai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Slack webhook URL≈ +4 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ocnaiPropose a patch to the maintainer