The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to interact with and process data from external project environments which could contain malicious content designed to influence agent behavior.
Ingestion points: The skill facilitates reading container logs (ddev logs), project files, and database exports.
Boundary markers: None explicitly mentioned in the skill instructions to separate external data from agent instructions.
Capability inventory: The skill utilizes wide-ranging capabilities including command execution (ddev exec), file system modifications, and network operations (ddev share).
Sanitization: No specific sanitization or validation steps are outlined for the data retrieved from DDEV containers or logs.
[PRIVILEGE_ESCALATION]: The troubleshooting section includes commands that require administrative privileges on the host system.
Evidence: The skill suggests running sudo lsof -i :80 to identify port conflicts.
[COMMAND_EXECUTION]: The skill's primary functionality is built around executing shell commands to manage Docker-based environments.
Evidence: Frequent use of ddev exec, ddev drush, ddev mysql, and script creation in .ddev/commands/ followed by chmod +x instructions.

ddev-expert