report-quality-review

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests radiology report content from RIS (Radiology Information System) and PACS (Picture Archiving and Communication System), which are external data sources that could potentially contain malicious instructions.
  • Ingestion points: Integration points defined in SKILL.md include RIS for report content and PACS for comparison study tracking.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the medical reports being audited.
  • Capability inventory: The agent calculates quality scores, generates feedback, and creates pending report alerts and escalation pathways.
  • Sanitization: There is no evidence of data sanitization, filtering, or validation of the clinical text before it is processed by the agent.
  • [NO_CODE]: The skill consists entirely of markdown configuration and JSON evaluation files. No executable scripts (Python, JavaScript, Shell) are provided, which significantly limits the risk of direct command execution or remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 05:08 PM