Skills/Docker MCP Catalog/slack

slack@0.6.2

CAUTION· install only

Publisher claims: "Interact with Slack Workspaces over the Slack API." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Docker MCP CatalogPublisher modelcontextprotocol · publishing for 726 daysInstalls 316KLast detonated 8 min 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso astral.sh — 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 under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- docker run -i --rm mcp/slack

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 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Instructs the agent to modify its persistent memory or instruction files; Collapsed <details> block carrying instructions. 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

MEDIUM
File permission modification commandsrc/memory/index.ts:600 · File permission modification command — agent changes file ownership/permissions// the umask can only narrow that. The chmod then restores any bits theFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Collapsed <details> block carrying instructionssrc/time/README.md:91 · Collapsed <details> block carrying instructions<summary>Using docker</summary> ```json { "mcpServers": { "time": { "command": "docker", "args": ["run", "-i", "--rm", "-e", "LOCAL_TIMEZONE", "mcp/time"] } } }Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/skills/issue-triage/SKILL.md:45 · Instructs the agent to modify its persistent memory or instruction files- **Pace every write loop** by `AGENTS.md` **Pacing GitHub writes**, andFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandsrc/memory/Dockerfile:65 · File permission modification command — agent changes file ownership/permissionsRUN mkdir /data && chown node:node /dataFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/lib/claude-cli.mjs:16 · npx invocation of non-well-known package — may execute untrusted code// so arguments go through the same `winShellArgs` quoting the npm/npx callFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/verify-dco.mjs:235 · File type combined with upload action — agent may exfiltrate local data files(code === 0 ? console.log : console.error)(output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandsrc/filesystem/package.json:25 · File permission modification command — agent changes file ownership/permissions"build": "tsc && shx chmod +x dist/*.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known package.claude/skills/client-smoke/SKILL.md:97 · npx invocation of non-well-known package — may execute untrusted code`MEMORY_FILE_PATH=… npx …` has no effect on the server; pass it with `-e`:Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/memory/index.ts:113 · npx invocation of non-well-known package — may execute untrusted code// and npm treats that tree as its own: a reinstall, an update or a cleared npxFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/skills/client-smoke/SKILL.md:206 · npx invocation of non-well-known package — may execute untrusted codenpx -y @modelcontextprotocol/[email protected] --web --protocol-era modern -- \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/memory/index.ts:129 · npx invocation of non-well-known package — may execute untrusted code"which npm manages: reinstalling or updating the server, or clearing the npx cache, " +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/skills/client-smoke/SKILL.md:38 · npx invocation of non-well-known package — may execute untrusted codeINSPECT="npx -y @modelcontextprotocol/inspector --cli"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collapsed <details> block carrying instructionssrc/time/README.md:186 · Collapsed <details> block carrying instructions<summary>Using Docker</summary> ```json { "mcp": { "servers": { "time": { "command": "docker", "args": ["run", "-i", "--rm", "mcp/time"] } } } } ```Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known package.claude/skills/local-dev/SKILL.md:89 · npx invocation of non-well-known package — may execute untrusted codenpx -y ./src/sequentialthinking # the workspace's bin, from its dist/Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill command.claude/skills/client-smoke/SKILL.md:138 · Process kill command — agent can terminate processestrap 'kill "$SERVER_PID" 2>/dev/null' EXIT # stops it however the subshell endsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/everything/package.json:25 · File permission modification command — agent changes file ownership/permissions"build": "tsc && shx cp -r docs dist/ && shx chmod +x dist/*.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill command.claude/skills/client-smoke/SKILL.md:141 · Process kill command — agent can terminate processeskill -0 "$SERVER_PID" 2>/dev/null || { echo "server exited before listening" >&2; exit 1; }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/lib/tsc-program.mjs:197 · npx invocation of non-well-known package — may execute untrusted code* client dir up the node_modules tree exactly as `npx --no-install tsc` walkedFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsscripts/smoke-servers.mjs:469 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesinstalled?.env,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionssrc/fetch/README.md:103 · Collapsed <details> block carrying instructions<summary>Using docker</summary> ```json { "mcpServers": { "fetch": { "command": "docker", "args": ["run", "-i", "--rm", "mcp/fetch"] } } } ```Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP).claude/skills/release/SKILL.md:734 · MCP server using network transport (SSE/HTTP) — data sent over networkecho "mcp-server-$s $v $(curl -s -o /dev/null -w '%{http_code}' "https://pypi.org/pypi/mcp-server-$s/$v/json")"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandscripts/skill-eval.mjs:607 · Process kill command — agent can terminate processes* @param {{ spawnFn?: typeof spawn, killProcess?: typeof process.kill }} [io]Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Collapsed <details> block carrying instructionssrc/git/README.md:247 · Collapsed <details> block carrying instructions<summary>Using docker</summary> * Note: replace '/Users/username' with a path that you want to be accessible by this tool * Note: the `-e` lines set the identitFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionssrc/fetch/README.md:164 · Collapsed <details> block carrying instructions<summary>Using Docker</summary> ```json { "mcp": { "servers": { "fetch": { "command": "docker", "args": ["run", "-i", "--rm", "mcp/fetch"] } } } } ```Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/smoke-servers.mjs:388 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn { ...env, ...(server.env?.(ctx) ?? {}), ...extra };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 package.claude/skills/client-smoke/SKILL.md:208 · npx invocation of non-well-known package — may execute untrusted codenpx -y @modelcontextprotocol/[email protected] --web --protocol-era legacy -- \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/skills/client-smoke/SKILL.md:29 · npx invocation of non-well-known package — may execute untrusted codenpx -y @modelcontextprotocol/inspector --cli <server command> [-- ] <inspector options>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandscripts/skill-eval.mjs:612 · Process kill command — agent can terminate processes{ spawnFn = spawn, killProcess = process.kill } = {},Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandscripts/gate-lease.test.mjs:658 · Process kill command — agent can terminate processes// Ctrl-C and a plain kill are the obvious ones; Ctrl-\ (SIGQUIT) is the oneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/smoke-servers.mjs:432 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: envFor(server, ctx, {}, installed?.env),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/sequentialthinking/package.json:25 · File permission modification command — agent changes file ownership/permissions"build": "tsc && shx chmod +x dist/*.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/memory/index.ts:111 · npx invocation of non-well-known package — may execute untrusted code// undefined for any other path. npx and npm install the server underFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive file system command detectedsrc/git/Dockerfile:36 · Destructive file system command detectedRUN apt-get update && apt-get install -y git git-lfs && rm -rf /var/lib/apt/lists/* \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/memory/package.json:25 · File permission modification command — agent changes file ownership/permissions"build": "tsc && shx chmod +x dist/*.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill command.claude/skills/client-smoke/SKILL.md:233 · Process kill command — agent can terminate processesgroup (`detached: true`) and kill the group when the script ends, so theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsscripts/skill-eval.test.mjs:436 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈59,169 tok
12 files · 80 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

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim modelcontextprotocol: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. 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.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. 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 Docker MCP Catalog, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim modelcontextprotocolPropose a patch to the maintainer