asrai-mcp-apikey@1.5.3
Asrai crypto analysis MCP server — API key auth for ADVANCED plan users.
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe only agent control-surface write is performed by an explicit CLI setup command and installs package-owned, purpose-aligned skill content. The API key is sent to the fixed Asrai service endpoint, with no inspected evidence of unrelated credential forwarding or malicious behavior.
Static reason
No blocking static signals were detected.
Trigger
A user runs the install-skill CLI command.
Impact
It adds Asrai crypto-analysis guidance to the agent’s available skills.
Mechanism
The command detects existing agent skill directories and copies the bundled skill and endpoint reference files there.
AI rationale
The only agent control-surface write is performed by an explicit CLI setup command and installs package-owned, purpose-aligned skill content. The API key is sent to the fixed Asrai service endpoint, with no inspected evidence of unrelated credential forwarding or malicious behavior.
Evidence
~/.openclaw/workspace/skills/asrai~/.openclaw/skills/asrai.agents/skills/asrai~/.agents/skills/asrai
Decision evidence
public snapshotAI called this Suspicious at 87.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- The package exposes install-skill as an explicit CLI command; no install lifecycle hook is declared.
- When run, the installer copies the package’s skill files into detected agent skill directories.
- The installed skill describes using Asrai tools for crypto analysis, consistent with the package’s purpose.
Evidence against
- The installer is not automatically triggered during package installation.
- The bridge sends the supplied API key to the Asrai service endpoint.
Behavioral surface
CryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
6 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(`✓ I
Medium
Ai Review Evidence
When run, the installer copies the package’s skill files into detected agent skill directories.
bin/install-skill.jsView on unpkg · L48Findings
1 High7 Medium3 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationbin/install-skill.js
MediumNetwork
MediumEnvironment Vars
MediumSuspicious Lifecycle Evidencepackage.json
MediumAi Review Evidencebin/install-skill.js
MediumAi Review Evidencebin/install-skill.js
MediumAi Review Evidenceskill/SKILL.md
MediumAi Review Evidencebin/asrai-mcp-apikey.js
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to asrai-mcp-apikey@1.5.3.
See all versions of asrai-mcp-apikey for other recorded verdicts.
- Review the evidence and your use of asrai-mcp-apikey@1.5.3 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.