fittings-rxnorm-ndc-crosswalk
Warn
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill downloads a JavaScript execution script (call.mjs) from the vendor's domain (https://fittings.sh/skill/call.mjs) and executes it using Node.js. While the source belongs to the author, runtime downloading and execution of code is a high-risk pattern for AI agents.
- [CREDENTIALS_UNSAFE]: The instructions prompt users to export a blockchain private key to the FITTINGS_PRIVATE_KEY environment variable. The documentation acknowledges that this key is stored in plaintext in the execution environment, which is a high-risk practice that could lead to credential theft.
- [COMMAND_EXECUTION]: The skill utilizes shell commands including curl for resource fetching and node for running the payment-enabled client.
- [EXTERNAL_DOWNLOADS]: The skill fetches remote assets including execution scripts and catalog metadata from fittings.sh via curl.
- [PROMPT_INJECTION]: The skill ingests untrusted drug identifiers. Evidence Chain: 1. Ingestion points: rxcui, name, and ndc parameters provided in the call. 2. Boundary markers: No delimiters or ignore-instructions warnings are defined. 3. Capability inventory: Network access via curl and script execution via node. 4. Sanitization: No evidence of input validation or sanitization is documented.
Audit Metadata