struktura-wyroku-pl

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data (legal judgment text).
  • Ingestion points: Ingests court judgment text via companion tools (saos-orzecznictwo, szukaj-orzeczen-v2) or direct user input.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings to prevent the agent from following malicious commands hidden within judgment text.
  • Capability inventory: The skill utilizes the Read tool for document access.
  • Sanitization: No sanitization, validation, or escaping of the external legal content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:31 PM
Security Audit — agent-trust-hub — struktura-wyroku-pl