@metronome/mcp
Score-based assessment (critical risk, 100/100). An AI review is available in the AI review tab.
Analysis record
- Analysed
- 4 months ago 23 July 2026
- Version
- v3.10.0
- Artifact
- SHA256 473a3feb…5a9f48
- Detail
- Full list
Evidence ledger
Ranked by severity · findings with a source location link to the code viewer
Network Indicators
Concrete URLs, domains, IPs, emails, and hashes extracted from the analyzed artifact.
Loading network indicators
Long lists can take a few seconds.
Finding Categories
MCP Server Analysis
MCP servers expose tools and resources to AI assistants. Unlike browser extensions, they run as standalone processes with direct system access. Tool definitions are analyzed for prompt injection, data exfiltration, and tool poisoning patterns.
AI Security Report
AI Security Review
Evidence context: threat category none; evidence quality weak.
This package presents a critical risk score based purely on volume indicators (111 IoCs, 132 malware signatures), but a detailed review reveals these are characteristic of bundled dependency noise rather than malicious intent.
Tool Poisoning: There are 0 findings for tool poisoning. This is the strongest positive signal—package descriptions and tool definitions are clean without hidden directives or invisible Unicode manipulation.
Credential Exfiltration: No evidence of targeted credential harvesting (e.g., .aws, .ssh, GITHUB_TOKEN) or secret exposure. The secret category count is 0.
Network & IoCs: The 8 network findings and 111 IoCs are likely artifacts of vendor development (GitHub Actions) or bundled libraries within the dist. There are no indications of exfiltration to unknown domains.
Malware Signatures: The 132 'malware-signature' hits combined with 0 'malware' classifications suggests these are heuristic matches on common utility code or minified bundles, not active payloads.
Conclusion: This appears to be a standard API wrapper for Metronome with a noisy scan profile due to build artifacts or CI/CD metadata. The absence of any MCP-specific threat vectors (tool poisoning, shadow tools, credential theft) supports a false positive verdict.
Key Reasons
- Zero tool-poisoning findings despite high risk score
- 132 'malware-signature' hits without a single 'malware' classification indicates heuristic noise
- Zero secret or credential access findings
- High finding count driven entirely by generic dependency IoCs (111) and code-smells (1)
False Positive Considerations
- IoC Extractor Garbage (IPv6 fragments, property chains, bundled deps)
- YARA Code-Smell Rules (broad signature matches on utility code)
- Bundled Dependencies (dist/ or node_modules inflating counts)
Reviewed 2026-04-12; recommended action: suppress false positive; model confidence 85%.
MCP version history
Risk trend by version
6 analyzed versions. Each point is the latest successful scan for that version; failed zero-score scans are hidden. Dates: First seen by Risky Plugins.
Pick any point on the chart, then open the Source tab to read that version's code.
Source Code Not Available
Source code is not available for this version of the extension.