AGENTSCORE-2026-0056
MCP package: zentric-protocol-mcp
Published 5/26/2026 · 0.1.7 → 0.1.8
Withdrawn after review on 2026-09-24
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.
zentric-protocol-mcp updated from 0.1.7 to 0.1.8. Score changed 95/100 to 65/100 (-30). Risk: LOW to ELEVATED. 2 findings.
95 → 65
Score
LOW → ELEVATED
Risk
WARN
Verdict
Findings
- critical prompt_injection_pattern: Package metadata contains prompt injection pattern: jailbreakNot a vulnerabilityThe package is a prompt-injection detector. The matched phrases describe or demonstrate the attacks it detects.
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: zentricprotocol