AGENTSCORE-2026-0177
MCP package: @oracle-agent/oracle
Published 10/23/2026 · 0.35.62 → 0.35.65
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.
@oracle-agent/oracle updated from 0.35.62 to 0.35.65. Score changed 95/100 to 90/100 (-5). Risk: LOW to LOW. 2 findings.
95 → 90
Score
LOW → LOW
Risk
ALLOW
Verdict
Findings
- low command_injection: Potential command injection: shell execution with template literal input (downgraded — mitigators detected in scope: test_fixture:test()
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: demigodzx