AGENTSCORE-2026-0174
MCP package: @martinloop/mcp
Published 10/19/2026 · 0.8.2 → 0.8.7
Automated, not yet reviewed
This advisory was generated automatically by a pattern-matching scanner when the package's score changed. Its findings have not been checked in the package source yet. Pattern matching produces false positives: when automated command-injection findings were first reviewed in source, most were not exploitable. Treat unreviewed findings as leads, not verdicts.
@martinloop/mcp updated from 0.8.2 to 0.8.7. Score changed 100/100 to 80/100 (-20). Risk: LOW to MODERATE. 1 finding.
100 → 80
Score
LOW → MODERATE
Risk
WARN
Verdict
Findings
- high command_injection: Potential command injection: shell execution with template literal input