The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl commands to interact with the AppDeploy API for service registration and managing application deployments.
[DATA_EXFILTRATION]: The skill is designed to transmit project source code and configuration files to the external domain api-v2.appdeploy.ai. This data transfer is the intended core functionality for the hosting service.
[CREDENTIALS_UNSAFE]: Authentication is managed via an API key stored in a local .appdeploy configuration file. The skill provides instructions for users to add this file to .gitignore to prevent accidental credential leakage to version control.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface through the get_deploy_instructions tool, which fetches instructions from a remote API that the agent is directed to follow before generating code.
Ingestion points: Remote instructions from get_deploy_instructions and file content retrieved via src_read and src_grep.
Boundary markers: Absent; there are no explicit delimiters or instructions to ignore potential commands within the data received from the API.
Capability inventory: The agent has access to filesystem operations and shell command execution via curl.
Sanitization: No validation or sanitization of the content returned from the remote API is performed before it is processed by the agent.

appdeploy