AGENTSCORE-2026-0112
MCP package: hive-intelligence
Published 8/29/2026 · 1.3.0 → 1.5.2
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.
hive-intelligence updated from 1.3.0 to 1.5.2. Score changed 90/100 to 85/100 (-5). Risk: LOW to LOW. 2 findings.
90 → 85
Score
LOW → LOW
Risk
ALLOW
Verdict
Findings
- medium excessive_dependencies: Package has 27 runtime dependencies (high attack surface)
- low command_injection: Potential command injection: shell execution with template literal input (downgraded — mitigators detected in scope: sanitizer:${REGISTRY_PACKAGE})