mcp-gitlab@2.3.28
CAUTION· install onlyPublisher claims: "GitLab MCP server for projects, merge requests, issues, pipelines, wiki, releases, and more" 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: 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
COMMA_IN_PASSWORD_HINTDOWNLOAD_TOKEN_SECRETDOWNLOAD_TOKEN_TTLGITLAB_OAUTH_CLIENT_IDGITLAB_OAUTH_CLIENT_SECRETGITLAB_OAUTH_REDIRECT_URIGITLAB_OAUTH_TOKEN_PATHGITLAB_OAUTH_TOKEN_SCRIPTGITLAB_OAUTH_TOKEN_SCRIPT_TIMEOUT_SECONDSGITLAB_PERSONAL_ACCESS_TOKENGITLAB_PERSONAL_ACCESS_TOKEN_FILEGITLAB_USE_OAUTHMIN_SECRET_BYTESOAUTH_STATELESS_SECRETOAUTH_STATELESS_SECRET_PREVIOUSor--oauth/--use-oauth/--oauth-stateless-modeConfiguration, not credentials: ComSpec, DEFAULT_NULL, EXCLUDED_FILE_PATTERN_MAX_COUNT, EXCLUDED_FILE_PATTERN_MAX_LENGTH, EXCLUDED_FILE_PATTERN_MAX_PROGRAM_SIZE, GITLAB_API_URL, GITLAB_MCP_REQUEST_BODY_LIMIT, GITLAB_PERMISSION_MODE, GITLAB_READ_ONLY_MODE, GITLAB_VERSION_CHECK_REGISTRY, JOB_LOG_MAX_PATTERN_LENGTH, LOG_FORMAT, MAX_PATTERN_LENGTH, PACKAGE_LATEST_PATH- Where it talks to
- no vendor host named in the codeAlso claude.ai, claude.com, chatgpt.com, client.example, a.example — 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 claude.ai, claude.com, chatgpt.com, client.example, a.example as well as its own vendor. The guard injects COMMA_IN_PASSWORD_HINT, DOWNLOAD_TOKEN_SECRET, DOWNLOAD_TOKEN_TTL, GITLAB_OAUTH_CLIENT_ID, GITLAB_OAUTH_CLIENT_SECRET, GITLAB_OAUTH_REDIRECT_URI, GITLAB_OAUTH_TOKEN_PATH, GITLAB_OAUTH_TOKEN_SCRIPT, GITLAB_OAUTH_TOKEN_SCRIPT_TIMEOUT_SECONDS, GITLAB_PERSONAL_ACCESS_TOKEN, GITLAB_PERSONAL_ACCESS_TOKEN_FILE, GITLAB_USE_OAUTH, MIN_SECRET_BYTES, OAUTH_STATELESS_SECRET, OAUTH_STATELESS_SECRET_PREVIOUS 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.
What changed since 2.3.27
vet-skills diff mcp-gitlab 2.3.27 2.3.28In the sandbox, this version reached for nothing 2.3.27 did not. Compared from the two recorded runs, not from source.
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 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: Hidden zero-width characters detected; URL with embedded credentials; URL with embedded credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
if (ch === " " || ch === "\t" || ch === "\n" || ch === "\r" || ch === "," || ch === "") {Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.// "https://user:pass@host" serializes as "https://host/"; keep the input's form.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* URLs: "http://alice:12,http://password:34,http://tail@host" givesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// A URL inside another URL's path or query ("...?next=https://user:pass@host")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* rather than silently collapsed: `"/etc/passwd"` would otherwise encode to aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// "https://a.example,https:user:[email protected]" is two URLs; the "@" after theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// by itself, so "https://alice:secret,https:word@host" stays one entry.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* host and port ("https://u:12/ab@host" has host "u"), so those forms use theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* there ("http://alice:p,http://w@host" gives "http://alice:p"), and an entryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const SKILL_INSTALL = "npx skills add zereight/gitlab-mcp --skill gitlab-mcp-skill";Fix: Pin versions and sources; vendor anything fetched at install time.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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim zereight: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.