rxnorm-normalize
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill documentation instructs users to download a helper script ('call.mjs') from 'https://fittings.sh/skill/call.mjs' and execute it via Node.js, creating a dependency on the vendor's distribution server.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill requires a blockchain private key ('FITTINGS_PRIVATE_KEY') to be stored in a plaintext environment variable. While used for signing authorizations, this poses a risk of credential exposure if the environment is compromised.
- [DYNAMIC_EXECUTION]: The 'call.mjs' script employs dynamic 'import()' calls to load necessary blockchain and networking libraries, such as viem and @x402/fetch.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted drug name inputs and interpolates them into API requests. 1. Ingestion point: 'name' argument in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Network fetch calls. 4. Sanitization: URL parameter encoding.
Audit Metadata