NYC

instrument-data-to-allotrope

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). This skill directly reads and parses arbitrary user-provided instrument files (CSV/XLSX/TSV/TXT/PDF) during runtime — see scripts/convert_to_asm.py (detect_instrument_type, flexible_parse, build_flexible_asm) and PDF extraction with pdfplumber — so it ingests untrusted third-party content that the agent will read/interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:40 PM