image-quality-audit

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze medical study data, protocols, and technical parameters to generate quality audits. This data-processing nature creates a theoretical attack surface where instructions could be embedded in the clinical records being analyzed.
  • Ingestion points: Processes clinical metadata, imaging parameters (Dose, SNR, spatial resolution), and protocol descriptions as defined in SKILL.md.
  • Boundary markers: The skill does not currently implement explicit delimiters or instruction-isolation warnings for the data it evaluates.
  • Capability inventory: The skill is limited to analytical operations and structured JSON reporting. No high-risk capabilities such as arbitrary shell execution, file system modifications, or network exfiltration were detected in the skill definitions.
  • Sanitization: There are no explicit validation or sanitization routines described for handling potentially malicious content within the clinical data inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 05:08 PM