AGENTSCORE-2026-0176
MCP package: @extension.dev/mcp
Published 10/22/2026 · 10.12.0 → 10.15.1
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.
@extension.dev/mcp updated from 10.12.0 to 10.15.1. Score changed 75/100 to 55/100 (-20). Risk: MODERATE to ELEVATED. 3 findings.
75 → 55
Score
MODERATE → ELEVATED
Risk
WARN
Verdict
Findings
- high command_injection: Potential command injection: shell execution with template literal input
- high unsafe_eval: Uses eval() with dynamic input
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: cezaraugusto