The Agent Skills Directory

[PROMPT_INJECTION]: The skill utilizes imperative markers such as '⛔ Critical Rules (never skip)' and 'Self-check before ending the turn (MANDATORY)' to strictly define agent behavior and response formatting requirements.
[COMMAND_EXECUTION]: The skill requires the execution of multiple system commands including npm, edgeone, mkdir, echo, and grep to manage dependencies and configuration.
[EXTERNAL_DOWNLOADS]: The skill downloads the edgeone CLI package from the public NPM registry. This utilizes a well-known service and the package is associated with the skill vendor.
[INDIRECT_PROMPT_INJECTION]: The skill contains logic to parse and display data from external command outputs, creating a surface for potential injection.
Ingestion points: Data is extracted from the stdout of the edgeone makers deploy command, specifically identifying fields like EDGEONE_DEPLOY_URL (found in SKILL.md).
Boundary markers: The instructions do not define delimiters or specific boundary guards for the parsed data.
Capability inventory: The skill possesses the ability to execute CLI tools, write to local configuration files (.edgeone/.token), and perform network operations via the vendor CLI.
Sanitization: There is no requirement for the agent to sanitize or validate the content extracted from command outputs before presenting it or using it in subsequent logic.

edgeone-makers-deploy