Summary
manthanghasadiya/mcpsec v2026-03-23 was classified as CRITICAL RISK with a risk score of 2657. Sigil detected 207 findings across 168 files, covering phases including provenance, code patterns, network exfiltration, obfuscation. Review the findings below before installing this package.
Package description: An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, ...
v2026-03-23
24 March 2026, 00:21 UTC
by Sigil Bot
Risk Score
2657
Findings
207
Files Scanned
168
Provenance
Findings by Phase
Phase Ordering
Phases are ordered by criticality, with the most dangerous at the top. Click any phase header to expand or collapse its findings. Critical phases are expanded by default.
Badge
Markdown
[](https://sigilsec.ai/scans/BBDDBCB8-85DF-4FEA-A5BD-31B81CAFAB55)HTML
<a href="https://sigilsec.ai/scans/BBDDBCB8-85DF-4FEA-A5BD-31B81CAFAB55"><img src="https://sigilsec.ai/badge/github/manthanghasadiya/mcpsec" alt="Sigil Scan"></a>Run This Scan Yourself
Scan your own packages
Run Sigil locally to audit any package before it touches your codebase.
Early Access
Get cloud scanning, threat intel, and CI/CD integration.
Join 150+ developers on the waitlist.
Get threat intelligence and product updates
Security research, new threat signatures, and product updates. No spam.
Other github scans
Believe this result is incorrect? Request a review or see our Terms of Service and Methodology.