The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides a command to download and install the dexpaprika-cli using a script hosted on the vendor's official GitHub repository: https://raw.githubusercontent.com/coinpaprika/dexpaprika-cli/main/install.sh.
[REMOTE_CODE_EXECUTION]: The provided installation method involves piping a remote shell script directly into the system shell (curl | sh). While this is a high-risk pattern, the source is the official repository of the skill's author and represents the standard distribution method for their tooling.
[COMMAND_EXECUTION]: The skill relies on executing various shell commands (dexpaprika-cli, curl) to perform its primary function of retrieving and displaying market data.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with and displays data from decentralized exchanges, such as token metadata and descriptions, which are controlled by external third parties.
Ingestion points: Data enters the agent's context through the outputs of the DexPaprika REST API, Streaming API, and the CLI tool (e.g., search results, token details).
Boundary markers: There are no specific instructions or delimiters provided to the agent to help it differentiate between system instructions and the untrusted content retrieved from the API.
Capability inventory: The agent is authorized to execute shell commands and perform network requests.
Sanitization: The skill does not describe any mechanisms for sanitizing or escaping the data fetched from external blockchain sources before it is processed.

dexpaprika-api