animal-pharmacy-search
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npx -y @nomadamas/k-skill@0to fetch instructions and manage skill components. The package originates from the author's own npm scope. - [REMOTE_CODE_EXECUTION]: Execution of the
@nomadamas/k-skillpackage allows the skill to run author-defined logic for managing skill files and interpreting commands. - [COMMAND_EXECUTION]: The skill instructions direct the agent to run a bundled Python script,
scripts/animal_pharmacy_mcp.py, which serves as the interface to the search service. - [DATA_EXFILTRATION]: The Python script performs network requests to
https://hkmedi.co.kr/pharmacy-mcpto retrieve pharmacy directory information and product data based on user queries. - [INDIRECT_PROMPT_INJECTION]: The skill processes structured data from an external API, representing a potential surface for indirect instruction ingestion.
- Ingestion points: Pharmacy names, addresses, and medicine metadata returned from the
hkmedi.co.krendpoint are parsed and displayed to the user. - Boundary markers: There are no explicit delimiters used to separate the external API data from the agent's core instructions.
- Capability inventory: The agent has access to shell execution (via npx) and network communication (via the Python script).
- Sanitization: The provided Python script validates the JSON schema of the API responses but does not sanitize the text content for downstream model processing.
Audit Metadata