healthkit-sync
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill documents functionality that ingests external data, which creates a surface for indirect prompt injection if malicious content is present in the source data.
- Ingestion points: Data enters the system context via
healthsync scan(processing QR data from the clipboard or local files) andhealthsync fetch(retrieving health data samples over the local network from an iOS device) as detailed inCLI-REFERENCE.md. - Boundary markers: There are no instructions or delimiters provided to the agent to treat ingested health data or pairing codes as untrusted or to ignore potentially embedded instructions.
- Capability inventory: The skill allows for the execution of
healthsyncCLI commands and the processing of their output within the agent's workflow. - Sanitization: While the security architecture in
SECURITY.mdmentions structural validation for pairing codes, there is no documented sanitization or escaping of the health sample content itself before it is returned to the user or processed by the agent.
Audit Metadata