The Agent Skills Directory

[SAFE]: The skill does not contain any malicious code, prompt injections, or obfuscated patterns.\n- [EXTERNAL_DOWNLOADS]: The skill references official and well-known dependencies from established registries (NPM and Crates.io) and official repositories from Ellipsis Labs. These are standard for the described integration and do not pose a security risk.\n- [DATA_EXFILTRATION]: No patterns of unauthorized data access or exfiltration were found. The skill correctly uses environment variables for configuration and explicitly advises against hardcoding sensitive information like private keys.\n- [INDIRECT_PROMPT_INJECTION]: The skill manages the attack surface of external market data ingestion through safety protocols. 1. Ingestion points: market data and exchange state are fetched from Phoenix APIs (SKILL.md). 2. Boundary markers: The skill instructs the agent to inform and validate with the user. 3. Capability inventory: The skill builds Solana instructions for trading (examples/orders). 4. Sanitization: Explicit rules require transaction simulation and user confirmation before execution (resources/risk-and-trading.md).

phoenix