AGENTSCORE-2026-0195
MCP package: @extension.dev/mcp
Published 11/17/2026 · 10.22.0 → 11.0.0
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 10.22.0 to 11.0.0. Score changed 75/100 to 70/100 (-5). Risk: MODERATE to MODERATE. 3 findings.
75 → 70
Score
MODERATE → MODERATE
Risk
WARN
Verdict
Findings
- high command_injection: Potential command injection: shell execution with template literal input
- low unsafe_eval: Uses eval() with dynamic input (downgraded — mitigators detected in scope: documentation_context:## 1)
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: cezaraugusto