abridge-upgrade-migration
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external clinical data, such as note templates and API responses, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: External data is retrieved via
sourceApi.get('/note-templates')and through the API version adapter logic defined inSKILL.md. - Boundary markers: The instructions and provided code snippets lack explicit delimiters or guidance for the agent to ignore potentially malicious content embedded within the processed healthcare data.
- Capability inventory: The skill is configured with access to tools such as
Bash(npm:*),Write, andEdit, which could be exploited if an injection attack is successful. - Sanitization: Although the code includes logic to strip EHR-specific fields, it lacks mechanisms to sanitize or validate the content against embedded instructions or malicious patterns.
Audit Metadata