AgentScore is for sale. View the assets and acquisition details →
high

AGENTSCORE-2026-0027

MCP package: @voybio/ace-swarm

Published 5/7/2026 · 2.4.0 → 2.4.1

Withdrawn after review on 2026-09-25

The high-severity findings that triggered this advisory were checked in the package source and are not vulnerabilities. The reasons are listed under each finding below. The advisory stays at this address so the record is not silently rewritten. Reviewed in source: the flagged code was located in the published package, read in context and traced from input to sink (AI-assisted), and every confirmation was re-audited independently.

@voybio/ace-swarm updated from 2.4.0 to 2.4.1. Score changed 95/100 to 75/100 (-20). Risk: LOW to MODERATE. 2 findings.

95 → 75
Score
LOW → MODERATE
Risk
WARN
Verdict

Findings

  • high command_injection: Potential command injection: shell execution with template literal inputExpected behaviourThe matched line uses an argument array. The package's run_tests and safe_edit_file tools run the command strings they are given, by design.
  • low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: vedatonuryilmaz