registry / asrai-mcp-apikey / 1.7.2
asrai-mcp-apikey@1.7.2
Asrai crypto analysis MCP server — API key auth for ADVANCED plan users.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe package has no install-time hook, and the flagged agent-directory writes occur only through an explicit skill-install command that copies this package’s skill files. The API key flows to the Asrai service used by the package, with no unrelated credential destination found.
Static reason
No blocking static signals were detected.
Trigger
The CLI contacts Asrai when run with a tool request; skill files are copied only when the install-skill command is invoked.
Impact
Expected service access and installation of the package’s own skill; no unrelated credential transfer or harmful default action was found.
Mechanism
The CLI sends the configured Asrai API key to mcp-api.asrai.me for the requested service operation. The installer copies bundled skill documentation into detected skill directories.
AI rationale
The package has no install-time hook, and the flagged agent-directory writes occur only through an explicit skill-install command that copies this package’s skill files. The API key flows to the Asrai service used by the package, with no unrelated credential destination found.
Network endpoints3
mcp-api.asrai.meapiasr.asrai.measrai-web:3000
Decision evidence
public snapshotAI called this Clean at 96.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The only lifecycle script is prepublishOnly, a sync check; there is no install, preinstall, or postinstall hook.
- Skill installation is a separately invoked command, and it copies this package’s skill and endpoint reference files.
- The CLI sends the supplied Asrai API key to mcp-api.asrai.me, the service this package is designed to access.
Evidence against
- The installer writes the package’s own skill files into detected agent skill directories when explicitly run.
- The API key is used in requests to the package’s documented Asrai service.
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, 'refere
Low
Ai Review Evidence
Skill installation is a separately invoked command, and it copies this package’s skill and endpoint reference files.
bin/install-skill.jsView on unpkg · L48Findings
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 Evidenceskill/SKILL.md
LowAi Review Evidencebin/install-skill.js
LowAi Review Evidencesrc/tools.js
Affected versions and remediation
This report applies to asrai-mcp-apikey@1.7.2.
See all versions of asrai-mcp-apikey for other recorded verdicts.
- Review the evidence and your use of asrai-mcp-apikey@1.7.2 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.