emergency-card

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/generate_emergency_card.py to process health data and generate HTML/PDF output cards. This behavior is consistent with the primary purpose of the skill.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted medical record files.\n
  • Ingestion points: Reads health data from multiple external files including data/手术记录/**/*.json and data/出院小结/**/*.json.\n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used when interpolating data into the final output.\n
  • Capability inventory: The skill has the capability to execute shell commands (Python scripts) and perform file system write operations (saveFile).\n
  • Sanitization: There is no evidence of sanitization or validation logic to filter potentially malicious instructions from the processed health records.\n- [SAFE]: The generated HTML output references assets like Tailwind CSS and Lucide icons from well-known content delivery networks (CDNs).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 04:14 PM