asrai-mcp-apikey@1.5.6

Asrai crypto analysis MCP server — API key auth for ADVANCED plan users.

AI Security Review

scanned 18d ago · by lpm-firewall-ai

The manifest has no install lifecycle hook, and the flagged installer only copies bundled skill files when invoked as a CLI command. Inspected runtime behavior is package-aligned, with no concrete attack identified.

Static reason

No blocking static signals were detected.

Trigger

A user invokes an exposed CLI command or calls an MCP tool.

Impact

No unauthorized mutation, credential disclosure to an unrelated recipient, or other concrete attack was established.

Mechanism

The installer copies bundled skill files; runtime API calls use the caller's key and tool arguments.

AI rationale

Decision evidence

public snapshot

AI called this Clean at 91.0% confidence as Benign with low false-positive risk.

Evidence for AI clean decision

package.json exposes CLI binaries and declares no install lifecycle hook; the flagged installer is a bin command that copies only the bundled skill files into detected skill directories.
The CLI sends its caller-provided API key to the Asrai MCP endpoint, and the API wrapper sends keys to Asrai service endpoints.
Account and alert operations are dispatched through tool calls using supplied arguments; no automatic account action was identified.

Evidence against

Behavioral surface

Source

CryptoEnvironmentVarsFilesystemNetwork

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 14 file(s), 144 KB of source, external domains: apiasr.asrai.me, asrai.me, github.com, mcp-api.asrai.me

Source & flagged code

7 flagged

bin/install-skill.jsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. #!/usr/bin/env node import { existssync, mkdirsync, copyfilesync } from 'fs'; import { join, dirname } from 'path'; import { homedir } from 'os'; import { fileurltopath } from 'url'; const __dirname = dirname(fileurltopath(import.meta.url)); const home = homedir(); const skill_src = join(__dirname, '..', 'skill', 'skill.md'); const endpoints_src = join(__dirname, '..', 'skill', 'references', 'endpoints.md');

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

bin/install-skill.jsView on unpkg

48function installTo(destDir, label) { mkdirSync(join(destDir, 'references'), { recursive: true }); copyFileSync(SKILL_SRC, join(destDir, 'SKILL.md')); copyFileSync(ENDPOINTS_SRC, join(destDir, 'references', 'endpoin

Low

Suspicious Lifecycle Evidence

package.json exposes CLI binaries and declares no install lifecycle hook; the flagged installer is a bin command that copies only the bundled skill files into detected skill directories.

bin/install-skill.js

Findings

1 High2 Medium9 Low

HighTrigger Reachable External Ai Agent Control Surface Mutationbin/install-skill.js

MediumNetwork

MediumEnvironment Vars

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

LowSuspicious Lifecycle Evidencepackage.json

LowSuspicious Lifecycle Evidencebin/install-skill.js

LowAi Review Evidencebin/asrai-mcp-apikey.js

LowAi Review Evidencesrc/tools.js

LowAi Review Evidencesrc/server.js

LowAi Review Evidencesrc/alert-tools.js

Affected versions and remediation

This report applies to asrai-mcp-apikey@1.5.6.

See all versions of asrai-mcp-apikey for other recorded verdicts.

Review the evidence and your use of asrai-mcp-apikey@1.5.6 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-18 10:53:53.047Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.

registry / asrai-mcp-apikey / 1.5.6

asrai-mcp-apikey@1.5.6

Asrai crypto analysis MCP server — API key auth for ADVANCED plan users.

AI Security Review

scanned 18d ago · by lpm-firewall-ai

Static reason

No blocking static signals were detected.

Trigger

A user invokes an exposed CLI command or calls an MCP tool.

Impact

No unauthorized mutation, credential disclosure to an unrelated recipient, or other concrete attack was established.

Mechanism

The installer copies bundled skill files; runtime API calls use the caller's key and tool arguments.

AI rationale

Decision evidence

public snapshot

AI called this Clean at 91.0% confidence as Benign with low false-positive risk.

Evidence for AI clean decision

package.json exposes CLI binaries and declares no install lifecycle hook; the flagged installer is a bin command that copies only the bundled skill files into detected skill directories.
The CLI sends its caller-provided API key to the Asrai MCP endpoint, and the API wrapper sends keys to Asrai service endpoints.
Account and alert operations are dispatched through tool calls using supplied arguments; no automatic account action was identified.

Evidence against

Behavioral surface

Source

CryptoEnvironmentVarsFilesystemNetwork

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 14 file(s), 144 KB of source, external domains: apiasr.asrai.me, asrai.me, github.com, mcp-api.asrai.me

Source & flagged code

7 flagged

bin/install-skill.jsView file

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

bin/install-skill.jsView on unpkg

Low

Suspicious Lifecycle Evidence

package.json exposes CLI binaries and declares no install lifecycle hook; the flagged installer is a bin command that copies only the bundled skill files into detected skill directories.

bin/install-skill.js

Findings

1 High2 Medium9 Low

HighTrigger Reachable External Ai Agent Control Surface Mutationbin/install-skill.js

MediumNetwork

MediumEnvironment Vars

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

LowSuspicious Lifecycle Evidencepackage.json

LowSuspicious Lifecycle Evidencebin/install-skill.js

LowAi Review Evidencebin/asrai-mcp-apikey.js

LowAi Review Evidencesrc/tools.js

LowAi Review Evidencesrc/server.js

LowAi Review Evidencesrc/alert-tools.js

Affected versions and remediation

This report applies to asrai-mcp-apikey@1.5.6.

See all versions of asrai-mcp-apikey for other recorded verdicts.

Review the evidence and your use of asrai-mcp-apikey@1.5.6 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-18 10:53:53.047Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.