registry / asrai-mcp-apikey / 1.9.0
asrai-mcp-apikey@1.9.0
Asrai crypto analysis MCP server — API key auth for ADVANCED plan users.
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe manifest has no install-time hook, and the flagged skill writer runs as an explicit CLI command that copies the package’s own skill files. API keys and exchange credentials are used with the Asrai service for the package’s documented features.
Static reason
No blocking static signals were detected.
Trigger
A user runs a CLI tool or invokes an MCP tool; skill files are copied only when the user runs install-skill.
Impact
Expected service requests and explicit skill setup; no unauthorized collection or control-surface mutation was identified.
Mechanism
The bridge sends the supplied Asrai key to the Asrai service. The positions tool sends the authenticated user’s configured exchange credentials to the configured Asrai API for position retrieval.
AI rationale
The manifest has no install-time hook, and the flagged skill writer runs as an explicit CLI command that copies the package’s own skill files. API keys and exchange credentials are used with the Asrai service for the package’s documented features.
Network endpoints2
mcp-api.asrai.meapiasr.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 manifest defines CLI binaries and has no install, preinstall, or postinstall hook.
- The explicit install-skill command copies only the package’s bundled skill and endpoint files into detected skill directories.
- The bridge resolves a user-provided Asrai API key and connects to https://mcp-api.asrai.me.
- Tool requests send the Asrai key to the Asrai API service; server mode uses its configured internal key.
- Exchange credentials are fetched only by the positions tool for the authenticated user and posted to the configured Asrai API.
Evidence against
Behavioral surface
CryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
5 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 unpkg48function installTo(destDir, label) {
mkdirSync(join(destDir, 'references'), { recursive: true });
copyFileSync(SKILL_SRC, join(destDir, 'SKILL.md'));
copyFileSync(ENDPOINTS_SRC, join(destDir, 'references', 'endpoints.md'));
console.log(`✓ Installed to ${label}: ${destDir}`);
}
let installed
Low
Ai Review Evidence
The explicit install-skill command copies only the package’s bundled skill and endpoint files into detected skill directories.
bin/install-skill.jsFindings
1 High2 Medium9 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationbin/install-skill.js
MediumNetwork
MediumEnvironment Vars
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
LowAi Review Evidencebin/install-skill.js
LowAi Review Evidencebin/asrai-mcp-apikey.js
LowAi Review Evidencesrc/tools.js
Affected versions and remediation
This report applies to asrai-mcp-apikey@1.9.0.
See all versions of asrai-mcp-apikey for other recorded verdicts.
- Review the evidence and your use of asrai-mcp-apikey@1.9.0 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.