The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill follows best practices for secret management by using environment variables for the API key.
[EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's official API endpoints at api.aisa.one. These requests are necessary for the skill's primary function of retrieving prediction market data.
[COMMAND_EXECUTION]: The skill utilizes curl and python3 to perform market queries and arbitrage calculations. The commands are clearly defined and use placeholders to prevent accidental execution of malformed strings.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes external data from third-party market APIs (Polymarket and Kalshi via AIsa).
Ingestion points: Data is ingested from https://api.aisa.one/apis/v1 through JSON responses in both the Python scripts and curl commands.
Boundary markers: No explicit boundary markers or 'ignore' instructions are provided in the prompt interpolation.
Capability inventory: The agent has the capability to execute shell commands (curl) and Python scripts, and it accesses the network.
Sanitization: Data is parsed as JSON, but there is no specific sanitization of string content to prevent the interpretation of natural language instructions by the LLM.

prediction-market-arbitrage