AGENTSCORE-2026-0168
MCP package: @extension.dev/mcp
Published 10/15/2026 · 10.11.2 → 10.12.0
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 10.11.2 to 10.12.0. Score changed 80/100 to 75/100 (-5). Risk: MODERATE to MODERATE. 2 findings.
80 → 75
Score
MODERATE → MODERATE
Risk
WARN
Verdict
Findings
- high unsafe_eval: Uses eval() with dynamic input
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: cezaraugusto