ripple
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses the
npx madgecommand inreference/analysis-techniques.mdto trace project dependencies. Thenpxutility downloads and executes code from the npm registry at runtime, which introduces a dependency on external third-party software. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted change descriptions and source code to assess production risk. According to
reference/blast-radius-quant.md, this process may involve accessing sensitive data sources like billing databases and analytics warehouses. Ingestion points: User-provided change descriptions and source code files. Boundary markers: No explicit delimiters are used to isolate untrusted data. Capability inventory: Recursive file reading, external package execution, and potential database querying. Sanitization: No input validation or filtering is defined for the analyzed content.
Audit Metadata