AGENTSCORE-2026-0093
MCP package: @firfi/huly-mcp
Published 7/31/2026 · 0.44.7 → 0.47.0
Withdrawn after review on 2026-09-24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.
@firfi/huly-mcp updated from 0.44.7 to 0.47.0. Score changed 80/100 to 60/100 (-20). Risk: MODERATE to ELEVATED. 4 findings.
80 → 60
Score
MODERATE → ELEVATED
Risk
WARN
Verdict
Findings
- medium excessive_dependencies: Package has 21 runtime dependencies (high attack surface)
- low command_injection: Potential command injection: shell execution with template literal input (downgraded — mitigators detected in scope: sanitizer:.exec(` PRAGMA, sanitizer:db.exec()
- high unsafe_eval: Uses eval() with dynamic inputNot a vulnerabilityAll matches are method definitions named eval in a bundled runtime, not calls to the global eval.
- low no_provenance: Package is not published with provenance attestations or trusted publishing. Published by: firfi