skills/ruvnet/ruflo/market-ingest/Gen Agent Trust Hub

market-ingest

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides a command-line alternative using npx @claude-flow/cli@latest. This involves downloading and executing a package from the npm registry, which is an expected part of the author's ecosystem.
  • [COMMAND_EXECUTION]: The skill utilizes Bash for managing data storage through CLI tools, supporting the primary function of data ingestion.
  • [PROMPT_INJECTION]: Ingesting market data from external REST APIs and CSV files represents a potential surface for indirect prompt injection.
  • Ingestion points: Step 1 identifies REST APIs and CSV files as primary data sources.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Subprocess execution via Bash and storage operations using MCP tools.
  • Sanitization: Step 2 (Normalization) involves mathematical transformations (Z-scores and relative price changes), which naturally filters out non-numeric instruction content before it reaches the vector index.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 03:18 PM