frontic-implementation
Warn
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [Unverifiable Dependencies & Remote Code Execution] (MEDIUM): The skill executes
npx @frontic/cli@latest generate, which downloads and runs external code from an untrusted source. This presents a risk of Remote Code Execution (RCE). Severity is reduced from HIGH as this operation is central to the skill's stated purpose. \n- [Dynamic Execution] (MEDIUM): The skill generates a local library and imports it at runtime (import client from '../../.frontic/generated-client'). This dynamic loading pattern is a security risk if the generation environment is not isolated. \n- [Indirect Prompt Injection] (LOW): The skill ingests external data that could contain malicious instructions. \n - Ingestion points: Data fetched via
fetch_api_calland the Frontic client. \n - Boundary markers: None. \n
- Capability inventory: Command execution via
npx. \n - Sanitization: No validation or sanitization of ingested API data is described.
Audit Metadata