claude-ally-health
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of untrusted external content provided by users, which serves as a potential injection vector.
- Ingestion points: The workflow relies on user-supplied 'symptom notes' and 'medical records' as primary data inputs in SKILL.md.
- Boundary markers: The instructions do not specify delimiters or delimiters to isolate untrusted user data from the system instructions.
- Capability inventory: The provided markdown file does not list any allowed-tools, shell execution commands, or network access requirements.
- Sanitization: There are no specified mechanisms for validating or escaping the content of medical records before analysis.
Audit Metadata