embeddings
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto execute theclaude-flowpackage, which involves downloading and running code from the npm registry if not present locally. - [COMMAND_EXECUTION]: Core functionality is implemented through shell commands, including database initialization, batch processing, and similarity searching.
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection through data ingestion points. Ingestion points:
--textparameter and--file documents.json. Boundary markers: None identified. Capability inventory: Subprocess execution vianpx. Sanitization: No sanitization or validation of the input data is specified before it is processed by the agentic-flow integration.
Audit Metadata