AGENTSCORE-2026-0136
MCP package: memcell
Published 9/29/2026 · 0.10.6 → 0.10.7
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.
memcell updated from 0.10.6 to 0.10.7. Score changed 100/100 to 95/100 (-5). Risk: LOW to LOW. 1 finding.
100 → 95
Score
LOW → LOW
Risk
ALLOW
Verdict
Findings
- low command_injection: Potential command injection: shell execution with template literal input (downgraded — mitigators detected in scope: sanitizer:spawn("cmd", [)