skills/lubluniky/quaq/quaq-ingest/Gen Agent Trust Hub

quaq-ingest

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process data from external, untrusted sources.
  • Ingestion points: The skill reads local files (e.g., 'tradingview_export.csv', 'tv_export.csv') and fetches data from external REST APIs (e.g., 'https://api.example.com/ohlcv').
  • Boundary markers: There are no explicit boundary markers or instructions to ignore potential instructions embedded within the data in the provided Python snippets.
  • Capability inventory: The skill can write data to the filesystem ('to_csv'), make external network requests ('requests.get'), and execute code via CLI ('python -c', 'zig build run').
  • Sanitization: While the skill documentation provides a manual validation checklist for the user, the provided code templates do not include automated input validation or sanitization logic.
  • [COMMAND_EXECUTION]: The skill provides instructions for executing Python code directly through the command line ('python -c') for data conversion tasks and running the 'zig build run' command to validate strategy configurations.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates fetching data from external network resources, specifically referencing the Binance REST API and providing templates for connecting to arbitrary third-party APIs using the 'requests' library.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:17 AM
Security Audit — agent-trust-hub — quaq-ingest