NYC

make-mips-interpreter

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly requires loading and interpreting arbitrary MIPS ELF binaries (Phase 1: "Minimal ELF Loader" — parse ELF header and load segments) and handling external files via syscalls (Phase 5: "support opening/reading external files"), meaning the agent will ingest and act on untrusted third-party/user-provided content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:18 PM