Skills/Glama/mcp-authprobe

mcp-authprobe@0.8.0

CAUTION· install only

Publisher claims: "Enables AI assistants to run authorized active authorization tests against remote MCP servers you own, including refresh token rotation and replay, redirect URI strictness, throttling, and consent CSRF checks, with JSON, SARIF, and Markdown reports." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher enigmacker · publishing for 7 daysInstalls 0Last detonated 7d 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Not enough was observed to say yet. Nothing executable in the bundle ran; the trace covers the install step only. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-authprobe` runs it now and prints the full answer.

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 2026-11-08 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Bidirectional text override characters detected; Hidden zero-width characters detected. 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
npx invocation of non-well-known packagesrc/consent/browser.ts:77 · npx invocation of non-well-known package — may execute untrusted code"The consent check needs the optional package playwright-core. Run it with: npx -p mcp-authprobe -p playwright-core mcp-authprobe consent-check <mcp-url>",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Bidirectional text override characters detectedsrc/redact.ts:32 · Bidirectional text override characters detected — may hide content direction/[\u0000-\u0008\u000B-\u001F\u007F-\u009F​-‏‪-‮⁠-⁤⁦-⁩]|[\u{E0000}-\u{E007F}]/gu;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packageaction.yml:118 · npx invocation of non-well-known package — may execute untrusted codenpx --yes --package "$pkg" mcp-authprobe "${args[@]}"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
URL to a private-network addresstest/address-policy.test.ts:54 · URL to a private-network address — a LAN or development targetexpect(plainHttpAllowed(new URL("http://10.0.0.5/"), true)).toBe(true);Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/lab-command.ts:34 · npx invocation of non-well-known package — may execute untrusted codenpx mcp-authprobe scan ${url} --allow-private --credentials-file lab-grant.jsonFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
URL to a private-network addresstest/address-policy.test.ts:54 · URL to a private-network address — a LAN or development targetexpect(plainHttpAllowed(new URL("http://10.0.0.5/"), true)).toBe(true);Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Hidden zero-width characters detectedsrc/redact.ts:32 · Hidden zero-width characters detected — may conceal content/[\u0000-\u0008\u000B-\u001F\u007F-\u009F​-‏‪-‮⁠-⁤⁦-⁩]|[\u{E0000}-\u{E007F}]/gu;Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/lab-command.ts:33 · npx invocation of non-well-known package — may execute untrusted codenpx mcp-authprobe login ${url} --allow-private --out lab-grant.jsonFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/lab-command.ts:32 · npx invocation of non-well-known package — may execute untrusted codenpx mcp-authprobe scan ${url} --allow-privateFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandsrc/credentials.ts:106 · File permission modification command — agent changes file ownership/permissionswarnings.push(`Credentials file ${path} is readable by other users; restrict it with chmod 600.`);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstest/address-policy.test.ts:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesawait expect(http.request({ url: "file:///etc/passwd" })).rejects.toThrow(/Unsupported URL scheme/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialstest/mcp-server.test.ts:98 · URL with embedded credentials — may be phishing or credential leakingconst res = await c.callTool({ name: "scan", arguments: { url: "https://user:[email protected]/mcp" } });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/lab-command.ts:35 · npx invocation of non-well-known package — may execute untrusted codenpx -p mcp-authprobe -p playwright-core mcp-authprobe consent-check ${url} --allow-privateFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Bidirectional text override characters detectedtest/posture.test.ts:48 · Bidirectional text override characters detected — may hide content direction{ check_id: "MCPP-X01", title: "t", severity: "high", confidence: "high", target: TARGET, location: "l", message: "evil \u001b[2J‮ access_token=abcdefgh123", fingerprint: "a" },Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Hidden zero-width characters detectedtest/redact.test.ts:21 · Hidden zero-width characters detected — may conceal contentexpect(neutralize("p​q")).toBe("p\\u{200b}q");Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Bidirectional text override characters detectedtest/posture.test.ts:57 · Bidirectional text override characters detected — may hide content directionexpect(p.findings[0]?.message).not.toMatch(/\u001b|‮|abcdefgh123/);Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Bidirectional text override characters detectedtest/redact.test.ts:20 · Bidirectional text override characters detected — may hide content directionexpect(neutralize("x‮y")).toBe("x\\u{202e}y");Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈37 tok
1 file · 71 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

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim enigmacker: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Bidirectional text override characters detected≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  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. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File permission modification command≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim enigmackerPropose a patch to the maintainer