AGENTSCORE-2026-0156
MCP package: mindpm
Published 10/7/2026 · 1.4.0 → 3.2.0
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.
mindpm updated from 1.4.0 to 3.2.0. Score changed 85/100 to 80/100 (-5). Risk: LOW to MODERATE. 3 findings.
85 → 80
Score
LOW → MODERATE
Risk
ALLOW
Verdict
Findings
- medium no_repository: Package has no repository link — source code is not verifiable
- low command_injection: Potential command injection: shell execution with template literal input (downgraded — mitigators detected in scope: sanitizer:.exec(` CREATE, sanitizer:${TASKS_COLUMNS})
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: umitkavala