The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were found during the analysis. The skill adheres to best practices for DeFi data modeling.\n- [EXTERNAL_DOWNLOADS]: The Python scripts perform network requests to a well-known service to retrieve market data.\n
Evidence: Scripts scripts/execution_cost.py and scripts/slippage_curve.py query the Jupiter quote API at quote-api.jup.ag.\n
Context: Jupiter is a well-known liquidity aggregator in the Solana ecosystem. This is standard functionality for an execution estimation tool.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents a potential surface for indirect injection as it processes data from external API responses and user inputs.\n
Ingestion points: Environment variables TOKEN_MINT and TRADE_SIZE_SOL in the scripts, and JSON responses from https://quote-api.jup.ag/v6/quote.\n
Boundary markers: Absent.\n
Capability inventory: Network access via the httpx library and console output. The skill does not have capabilities for file-system modification or code execution.\n
Sanitization: Responses are parsed as standard JSON for numerical calculations; the content is not executed as code or instructions.

slippage-modeling