The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local Python scripts to interact with the Codemagic API. These scripts are invoked to list builds, fetch logs, manage environment variables, and control build lifecycles.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to well-known service domains to function: * Fetches the OpenAPI v3 schema from codemagic.io to maintain up-to-date API endpoints. * Retrieves build metadata, status updates, and build logs from api.codemagic.io.
[PROMPT_INJECTION]: The skill processes external, potentially attacker-controlled data, creating a surface for indirect prompt injection. * Ingestion points: Build logs, commit messages, and failure summaries are retrieved from the Codemagic API and presented to the agent. * Boundary markers: The scripts do not use specific delimiters or include instructions for the agent to ignore instructions embedded within the build data. * Capability inventory: The skill allows the agent to start builds, cancel running builds, and modify application environment variables. * Sanitization: There is no evidence of sanitization or filtering applied to the logs or commit messages before they are processed by the agent.

codemagic-builds