registry / asrai-mcp-apikey / 1.5.4
asrai-mcp-apikey@1.5.4
Asrai crypto analysis MCP server — API key auth for ADVANCED plan users.
AI Security Review
scanned 20d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the agent-directory mutation is performed by a separate user-run command that copies this package’s own skill files. The API key is sent to the package’s stated Asrai service for its analysis API, with no unrelated recipient or concrete attack behavior identified.
Static reason
No blocking static signals were detected.
Trigger
A user runs a CLI command, connects an MCP client, or explicitly runs the skill installer.
Impact
No harmful effect was established; the observed behavior provides the package’s stated analysis service and installs its own skill files.
Mechanism
The bridge forwards API tool requests to the Asrai service using the supplied key; the installer copies bundled skill documentation when it detects a supported skills directory.
AI rationale
The manifest has no install lifecycle hook, and the agent-directory mutation is performed by a separate user-run command that copies this package’s own skill files. The API key is sent to the package’s stated Asrai service for its analysis API, with no unrelated recipient or concrete attack behavior identified.
Evidence
bin/install-skill.jsskill/SKILL.mdskill/references/endpoints.md
Network endpoints1
mcp-api.asrai.me
Decision evidence
public snapshotAI called this Clean at 96.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The full manifest registers CLI commands and dependencies but defines no lifecycle scripts.
- The installer copies this package’s bundled skill files only when it finds a supported agent skills directory.
- The bridge uses the supplied API key to connect to the package’s hosted MCP service and forwards tool requests.
- The API client sends the user key to the Asrai service for its requested API calls.
Evidence against
Behavioral surface
CryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
7 flaggedbin/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 unpkg21const SKILL_SRC = join(__dirname, '..', 'skill', 'SKILL.md');
const ENDPOINTS_SRC = join(__dirname, '..', 'skill', 'references', 'endpoints.md');
// Candidate install paths
const candidates = [
{
name: 'OpenClaw',
path: join(home, '.openclaw', 'workspace', 'skills', 'asrai'),
detect: join(home, '.openclaw', 'workspace
Low
Ai Review Evidence
The installer copies this package’s bundled skill files only when it finds a supported agent skills directory.
bin/install-skill.jsFindings
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 Evidencepackage.json
LowAi Review Evidencebin/install-skill.js
LowAi Review Evidencebin/install-skill.js
LowAi Review Evidencebin/install-skill.js
LowAi Review Evidencebin/asrai-mcp-apikey.js
Affected versions and remediation
This report applies to asrai-mcp-apikey@1.5.4.
See all versions of asrai-mcp-apikey for other recorded verdicts.
- Review the evidence and your use of asrai-mcp-apikey@1.5.4 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: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.