Skills/npm/agent-trust-mcp

agent-trust-mcp@1.1.10

CAUTION

Publisher claims: "PII/secret redaction, email checks, sanctions screening, OSV lookups and an MCP server pre-check." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher fairquery · publishing for 28 daysInstalls 0Last detonated 5d ago
What would fix thisWatchDispute verdict

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
APIFY_TOKENConfiguration, not credentials: MCP_TRANSPORT
Where it talks to
no vendor host named in the codeAlso apify.com, treas.gov, europa.eu, fcdo.gov.uk, un.org, osv.dev — 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
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 apify.com, treas.gov, europa.eu, fcdo.gov.uk, un.org, osv.dev as well as its own vendor. The guard injects APIFY_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @fairquery/agent-trust-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) on 2026-11-09 and scored it 73/100 (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; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 26 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
6.0sprocessdependency install exit 0
26sclaimed14 tools: pii_list_detectors, pii_scan_text, pii_redact_text, pii_restore_text, pii_guard_documents, email_check_syntax, email_validate_deliverability, sanctions_list_sources, sanctions_screen_names, osv_query_packages, osv_get_vulnerability, osv_audit_dependencies, trust_screen_lead, mcp_server_precheck
26sprocessscript backend runs setup only
26sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/lib/mcp-precheck.js:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…reveal|show)\b(?:\s+\w+){0,8}\s+(?:the\s+)?user\b/i; const SECRET_WORD = /\b(?:\.env\b|id_rsa|id_ed25519|\.ssh\b|credentials?|api[_ -]?keys?|access[_ -]?tokens?|sec…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/lib/mcp-precheck.js:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…~][a-z0-9-._~]*\/)?[a-z0-9-~][a-z0-9-._~]*$/i; const SENSITIVE_BASENAME = /^(?:\.env(?:\..*)?|id_rsa|id_dsa|id_ecdsa|id_ed25519|known_hosts|authorized_keys|\.npmrc|…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Prompting user to enter sensitive credentialsdist/common.js:138 · Prompting user to enter sensitive credentials — social engineeringreturn undefined; // tokens never contain whitespace; e.g. "paste your token here"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
AWS access key pattern detecteddist/server.js:144 · AWS access key pattern detected — possible hardcoded or harvested keyEXAMPLE: '{"texts":["Mail [email protected], key AKIAIOSFODNN7EXAMPLE"]} -> 2 findings: EMAIL (masked "j***@a***.com"), AWS_ACCESS_KEY; risk_level "critical".',Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
AWS access key pattern detecteddist/server.js:58 · AWS access key pattern detected — possible hardcoded or harvested key…_TOTAL_CHARS.toLocaleString('en-US')} chars. Example: ["Mail [email protected], key AKIAIOSFODNN7EXAMPLE"]`); const localDetectArgs = { entityTypes: z.array(z.string().max(40)).max…Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
AWS access key pattern detecteddist/server.js:250 · AWS access key pattern detected — possible hardcoded or harvested key…000,000 chars; one billed document row each. Example: ["Mail [email protected], key AKIAIOSFODNN7EXAMPLE"]'), documentUrls: z.array(z.string().url().max(2000)).max(100).opt…Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03

Cost to the agent

Instructions loaded
≈99 tok
1 file · 24 in bundle
Tool list per prompt
≈13,304 tok
14 tools · 950 per tool
Handshake
1634 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 1906

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 @fairquery/agent-trust-mcp@1.1.10 as of 5d ago. This is the package itself, not its dependencies.

What would make this Verified

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim fairquery: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  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. AWS access key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim fairqueryPropose a patch to the maintainer