trace-mcp@3.36.0
Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe scanner’s similarity labels are not proof of maliciousness. The inspected citations show an install chain and flagged paths, but no source evidence in those excerpts establishes an attack, so this package is marked clean.
Decision evidence
public snapshot- package.json defines a postinstall chain and points to the package’s own setup scripts.
- The two flagged bundle locations contain agent configuration path constants; the cited excerpts do not establish a write or control hijack.
- The flagged scripts are screenshot, upgrade, fixture, benchmark, performance, and documentation utilities; their cited excerpts show those stated roles.
- No confirmed malicious behavior was identified in the inspected evidence.
Source & flagged code
26 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to trace-mcp@3.36.0.
See all versions of trace-mcp for other recorded verdicts.
- Review the evidence and your use of trace-mcp@3.36.0 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.