The Agent Skills Directory

[SAFE]: No malicious patterns or obfuscation detected. The skill provides legitimate instructions for application listing and publication.
[COMMAND_EXECUTION]: Uses yarn twenty dev:build and yarn twenty app:publish. These are platform-specific CLI tools from the vendor (twentyhq) used for standard development and deployment workflows.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted local files. * Ingestion points: package.json, README.md, src/application-config.ts (SKILL.md). * Boundary markers: None explicitly defined for these files. * Capability inventory: Subprocess execution via yarn twenty commands (SKILL.md). * Sanitization: No explicit sanitization or validation of the file contents before processing is mentioned.

publish-app