orthodontist
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external patient data, such as clinical records and diagnostic images, which could serve as a vector for indirect prompt injection if the source data is malicious. However, the skill possesses no capabilities to interact with the system or network, significantly limiting the potential impact.
- Ingestion points: Patient photographs, digital models, panoramic/lateral cephalometric radiographs, and clinical history as described in
SKILL.md. - Boundary markers: Absent; the instructions do not suggest using specific delimiters or safety warnings when processing external patient data.
- Capability inventory: None; the skill configuration does not enable any tools, subprocesses, network operations, or file-system writing.
- Sanitization: None; the skill does not define methods for validating or filtering content within the records it analyzes.
Audit Metadata