The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The CLI reference document suggests installing a tool by downloading and executing a shell script from a remote source.
Evidence: curl -sSL https://raw.githubusercontent.com/coinpaprika/coinpaprika-cli/main/install.sh | sh in references/cli-reference.md.
[EXTERNAL_DOWNLOADS]: The skill downloads an installation script and references various external SDKs and documentation hosted on GitHub and the vendor's official domain.
Fetches configuration and code from raw.githubusercontent.com and github.com repositories managed by the coinpaprika organization.
[DATA_EXFILTRATION]: The skill is designed to perform network operations to external API endpoints to retrieve market data.
Communicates with api.coinpaprika.com, api-pro.coinpaprika.com, and mcp.coinpaprika.com.
[COMMAND_EXECUTION]: The documentation provides numerous examples of shell commands for the agent to execute for data retrieval and configuration.
Extensive use of curl and jq for API interaction.
Functional CLI commands such as coinpaprika-cli onboard and coinpaprika-cli tickers.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing external data from a third-party API.
Ingestion points: Data retrieved from api.coinpaprika.com as documented in SKILL.md and references/openapi.yml.
Capability inventory: Shell execution capabilities using curl and the vendor-provided CLI tool.
Boundary markers: Absent; no specific delimiters or warnings are provided to the agent to isolate untrusted external content.
Sanitization: Absent; the skill documentation does not mention validation or sanitization of external API responses before processing.

coinpaprika-api