Skills/npm/corkcrm-mcp

corkcrm-mcp@0.53.0

CAUTION· startup only

Publisher claims: "MCP server for corktasks.com (CorkCRM PM)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher corkcrm · publishing for 223 daysInstalls 8,636Last detonated 25 h ago

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: 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
CORK_API_KEYConfiguration, not credentials: CONVEX_URL, CORK_APP_URL, CORK_DOWNLOAD_DIR, CORK_MCP_NOW, RESOURCE_METADATA_PATH
Where it talks to
no vendor host named in the codeAlso convex.site, corktasks.com — 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
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names convex.site, corktasks.com as well as its own vendor. The guard injects CORK_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y corkcrm-mcp

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 (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-13 and scored it 79/100 (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; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 27 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.1sprocessdependency install exit 0
27sclaimedstartup only: exited (0) before answering · at getConvexUrl (file:///tmp/ks-detonate-H9VovF/task/home/work/acme-api/.claude/skills/corkcrm-mcp/dist/auth.js:19:15) at file:///tmp/ks-detonate-H9VovF/task/home/work/acme-api/.claude/skills/corkcrm-mcp/dist/index.js:18:16 at process.processTicksAndRejections (node:internal/process/task_queues:103:5) Node.js v22.23.5
27sprocessscript backend runs setup only
27sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/cli.js:93 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst tmp = join(dir, `.credentials.${randomBytes(6).toString("hex")}.tmp`);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/formatTree.js:58 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst rows = [...env.rows].sort((a, b) => (b.state_since ?? "").localeCompare(a.state_since ?? "") || a.name.localeCompare(b.name));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/format.js:289 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslines.push(...env.rows.map((r) => `- ${formatRow(r, { assigneeId, lead, where })}`));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hidden zero-width characters detecteddist/descriptionFile.js:70 · Hidden zero-width characters detected — may conceal contentconst body = decoded.replace(/^/, "").replace(/\r\n/g, "\n");Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Access to sensitive file pathsdist/formatTree.js:75 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files...env.rows.map((r) => `${number(r.simple_id)} ${bars([oneLine(r.name), r.project_state?.name ?? "no state", r.project_type?.name])}`),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondist/cli.d.ts:17 · File type combined with upload action — agent may exfiltrate local data files… saves it to\n ~/.config/corktasks/credentials.json, readable only by you (0600).\n --url is the Convex site URL, ending .convex.site; it defaults to\n CONVEX_URL, then to the URL already saved, then to https://hip-dog-509.convex.site.\n c…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Destructive file system command detecteddist/writeSchemas.js:212 · Destructive file system command detected// add_project_summary (alpha-8369). The summary is about, needs, and milestones (alpha-8595); parts, the formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈46 tok
1 file · 77 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for corkcrm-mcp@0.53.0 as of 25 h ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim corkcrm: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim corkcrmPropose a patch to the maintainer