The Agent Skills Directory

[COMMAND_EXECUTION]: The skill interacts with the platform's CLI tool (mcporter) and the curl utility using subprocess.Popen and subprocess.run. These calls are constructed using argument lists rather than shell strings, which effectively prevents shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The script dsl-v4.py fetches market data from the Hyperliquid API (https://api.hyperliquid.xyz/info) via curl. Hyperliquid is the intended exchange for this trading strategy, making this a legitimate and safe data reference.
[CREDENTIALS_UNSAFE]: The configuration files and setup scripts (tiger-config.json, tiger-setup.py) use placeholders such as <your_strategy_wallet> and <your_strategy_id>. No hardcoded private keys, API tokens, or other sensitive credentials were found in the codebase.
[PROMPT_INJECTION]: The SKILL.md and README.md files provide technical instructions for agent operation. No instructions were found that attempt to override the AI agent's safety protocols or core behavioral guidelines.
[SAFE]: The skill includes robust error handling, such as per-asset try/except blocks in scanning loops to prevent a single asset's data failure from stopping the entire system. It also utilizes atomic file operations to maintain state integrity.

tiger-strategy