AGENTSCORE-2026-0123
MCP package: hive-intelligence
Published 9/10/2026 · 1.5.3 → 1.6.0
Withdrawn after review on 2026-09-25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.
hive-intelligence updated from 1.5.3 to 1.6.0. Score changed 85/100 to 70/100 (-15). Risk: LOW to MODERATE. 2 findings.
85 → 70
Score
LOW → MODERATE
Risk
WARN
Verdict
Findings
- medium excessive_dependencies: Package has 25 runtime dependencies (high attack surface)
- high command_injection: Potential command injection: shell execution with template literal inputNot a vulnerabilityThe URL comes from a fixed four-entry map, and an unknown key exits before any command runs.