The Agent Skills Directory

[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag, which allows the agent to transmit command results (potentially containing domain configurations or account metadata) to an arbitrary external URL via HTTP POST.
[EXTERNAL_DOWNLOADS]: The installation process fetches software from external sources, specifically the @mvanhorn/printing-press package on NPM and the github.com/mvanhorn/printing-press-library repository on GitHub.
[COMMAND_EXECUTION]: The skill requires executing shell commands for installation (npx, go install), configuration (cf-domain-pp-cli auth), and operational tasks, which involves running a binary locally on the host system.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingests and processes data from external Cloudflare APIs.
Ingestion points: Data enters the context via domain-search and domain-check commands in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore instructions embedded within the API responses.
Capability inventory: The skill can execute shell commands (bash tool), write to files via the --deliver flag, and perform network operations through the CLI's native API interactions and webhook feature.
Sanitization: There is no evidence of sanitization or validation of the content retrieved from the external API before it is processed by the agent.

pp-cf-domain