mcp-authscan@1.1.37
VERIFIED· install onlyPublisher claims: "MCP AuthScan" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 60 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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: Verified 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
MCP_AUTHSCAN_SIGNING_KEYMCPAUTHSCAN_CLIENT_IDMCPAUTHSCAN_CLIENT_SECRETMCPAUTHSCAN_CROSS_TENANTMCPAUTHSCAN_FOREIGN_IDMCPAUTHSCAN_RATEMCPAUTHSCAN_REDIRECT_URIMCPAUTHSCAN_TENANT_TOKENMCPAUTHSCAN_TOKENMCPAUTHSCAN_TOKEN_ENDPOINT_AUTH_METHODMCPAUTHSCAN_TOKEN_UNAUTHor--acquire-tokenConfiguration, not credentials: HARNESS, MATRIX, TS_DRIVER- Where it talks to
- no vendor host named in the codeAlso decoy.invalid, vata-probe-one.invalid, vata-probe-two.invalid, expected.invalid, schemastore.org, foreign-resource.invalid, evil.example, githubusercontent.com, boardy.invalid, probe.invalid — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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 decoy.invalid, vata-probe-one.invalid, vata-probe-two.invalid, expected.invalid, schemastore.org, foreign-resource.invalid, evil.example, githubusercontent.com, boardy.invalid, probe.invalid as well as its own vendor. The guard injects MCP_AUTHSCAN_SIGNING_KEY, MCPAUTHSCAN_CLIENT_ID, MCPAUTHSCAN_CLIENT_SECRET, MCPAUTHSCAN_CROSS_TENANT, MCPAUTHSCAN_FOREIGN_ID, MCPAUTHSCAN_RATE, MCPAUTHSCAN_REDIRECT_URI, MCPAUTHSCAN_TENANT_TOKEN, MCPAUTHSCAN_TOKEN, MCPAUTHSCAN_TOKEN_ENDPOINT_AUTH_METHOD, MCPAUTHSCAN_TOKEN_UNAUTH 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 1.1.20
vet-skills diff mcp-authscan 1.1.20 1.1.37This version reaches for something 1.1.20 did not: 3 new hosts (decoy.invalid, expected.invalid, probe.invalid) · 2 new credential variables (MCPAUTHSCAN_RATE, MCP_AUTHSCAN_SIGNING_KEY). Compared from the two recorded runs, not from source.
- New hosts
- decoy.invalid, expected.invalid, probe.invalid
- New credential variables
- MCPAUTHSCAN_RATE, MCP_AUTHSCAN_SIGNING_KEY
1.1.20 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
child = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r"(?i)(~/\.ssh|id_rsa|/etc/passwd|/etc/shadow|\.env\b"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if "@" not in ev and any(seg in pl for seg in (".config.", "/scripts/", "tsdown", "vite.config", "webpack", "rollup", "/config/", ".env.example")):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.child = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# No proxy credentials, cookie jar, netrc authentication, or redirect scopeFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pr = subprocess.Popen([sys.executable, need(os.path.join(H, "fixture.py")), mode, str(port)], cwd=H, stdout=f, stderr=subprocess.STDOUT)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(cmd, cwd=H, capture_output=True, text=True, timeout=90)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.commit_sha = subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.repo_url = subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "mcp_authscan/conformance_token.py", log, prefix], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.branch = subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.pr = subprocess.Popen([sys.executable, need(os.path.join(H, "fixture.py")), mode, str(port)], cwd=H, stdout=f, stderr=subprocess.STDOUT)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(cmd, cwd=H, capture_output=True, text=True, timeout=90)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.commit_hash = subprocess.check_output(["git", "rev-parse", "--short", "HEAD"], cwd="/home/lhmisme/mcp-authscan", text=True).strip()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.clone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "mcp_authscan/conformance_meta.py", log, sink], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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.