registry / asrai-mcp-apikey / 1.6.2
asrai-mcp-apikey@1.6.2
Asrai crypto analysis MCP server — API key auth for ADVANCED plan users.
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe flagged agent-directory writes occur only through an explicitly invoked installer and place the package's own skill files in Asrai-specific directories. The API key is caller-provided and sent to the Asrai service; inspected source showed no concrete attack behavior.
Static reason
No blocking static signals were detected.
Trigger
A user invokes install-skill or launches the MCP bridge with an API key.
Impact
No unrequested control-surface change, credential harvesting, or unrelated credential transfer was established.
Mechanism
The installer copies the bundled skill files into detected Asrai skill directories. The bridge forwards the supplied key to the configured Asrai MCP endpoint.
AI rationale
The flagged agent-directory writes occur only through an explicitly invoked installer and place the package's own skill files in Asrai-specific directories. The API key is caller-provided and sent to the Asrai service; inspected source showed no concrete attack behavior.
Network endpoints2
mcp-api.asrai.meapiasr.asrai.me
Decision evidence
public snapshotAI called this Clean at 92.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes install-skill as a command and has no npm lifecycle script; the bundled skill documents an explicit invocation.
- The installer copies only this package's skill and endpoint reference into detected Asrai skill directories when invoked.
- The bridge obtains its API key from the caller's command line or ASRAI_KEY and sends it to the Asrai MCP service.
- Inspected dependency excerpts show MCP transports, environment-file parsing, an HTTP server entrypoint, and a PostgreSQL pool used by the service.
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 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 = 0;
for (const c of candidates) {
if (existsSync(c.detect)) {
installTo(c.path, c.name);
installed++;
}
}
if (installed === 0) {
console.log('No agent
Low
Ai Review Evidence
The installer copies only this package's skill and endpoint reference into detected Asrai skill directories when invoked.
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 Evidenceskill/SKILL.md
LowAi Review Evidencebin/install-skill.js
LowAi Review Evidencebin/asrai-mcp-apikey.js
LowAi Review Evidencesrc/tools.js
LowAi Review Evidencesrc/tools.js
Affected versions and remediation
This report applies to asrai-mcp-apikey@1.6.2.
See all versions of asrai-mcp-apikey for other recorded verdicts.
- Review the evidence and your use of asrai-mcp-apikey@1.6.2 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.