The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx --yes bunjang-cli, which downloads and executes an external tool from the npm registry. The package and its associated repository (pinion05/bunjangcli) are not provided by an established or verified organization.
[COMMAND_EXECUTION]: The skill relies on executing shell commands to perform marketplace operations, including authentication (auth login), data retrieval, and exporting files to the local system.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes untrusted data from a public marketplace (Bunjang).
Ingestion points: Data enters the agent's context through search results (search) and item details (item get).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the marketplace data.
Capability inventory: The agent has the ability to write to the file system (using the --output flag) and perform network operations via the CLI tool.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from item descriptions or titles before processing.

bunjang-search