nhis-care-checkup-search
Warn
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructions direct the agent to execute an external package using
npx -y @nomadamas/k-skill@0, which downloads and runs code from the npm registry at runtime.- [EXTERNAL_DOWNLOADS]: Fetches and updates instructions and helper files from external sources, including the npm registry and a public GitHub repository (github.com/NomaDamas/k-skill).- [COMMAND_EXECUTION]: Employs shell commands (curl) to request data from an external proxy server (k-skill-proxy.nomadamas.org).- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from external institutional search APIs.\n - Ingestion points: Data is fetched from the NHIS search API via a proxy in
instruction.md.\n - Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions that might be embedded in the retrieved institutional data.\n
- Capability inventory: The skill has the ability to execute shell commands (
curl,npx).\n - Sanitization: No evidence of input sanitization or output escaping for the external data is provided.
Audit Metadata