structured-reporting

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: A detailed security audit of the skill instructions, templates, and associated files found no evidence of malicious patterns. The skill is focused exclusively on medical reporting standards and does not request or use any sensitive system permissions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process free-text radiology reports, which creates a theoretical surface for indirect prompt injection. However, the risk is negligible as the skill lacks access to any dangerous capabilities. 1. Ingestion points: The free_text_report input in the conversion function documented in SKILL.md. 2. Boundary markers: Absent; no specific delimiters are defined to isolate user-provided data. 3. Capability inventory: The skill has no access to file writing, network communication, or shell command execution. 4. Sanitization: No input filtering or validation logic is specified in the illustrative code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:48 AM