crypto-kline-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides multiple Python CLI tools (crypto_analyzer.py, write_to_notion.py, setup.py) intended to be executed by the agent to perform its core functions.
- [EXTERNAL_DOWNLOADS]: The installation scripts (install.sh) and documentation (INSTALL.md) instruct the user/agent to download and install several third-party libraries from the Python Package Index (PyPI) including ccxt, pandas-ta, and notion-client.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from two main sources: real-time market data from the Binance API and user-supplied notes/files for Notion uploading. This creates a surface for indirect prompt injection if the external data or processed notes contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: crypto_analyzer.py (Binance API data), write_to_notion.py (user-supplied text via --content or --file arguments).
- Boundary markers: None present in the agent instructions to help distinguish between data and instructions.
- Capability inventory: The skill has the capability to read/write files (logs and configuration) and perform network operations (connecting to Binance and Notion APIs).
- Sanitization: There is no evidence of specific sanitization or filtering of the ingested content before it is processed by the agent.
Audit Metadata