The Agent Skills Directory

[COMMAND_EXECUTION]: The skill interacts with the local gws binary to perform administrative tasks on Google Classroom, such as creating courses, managing invitations, and viewing user profiles.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external Google Classroom API resources, creating a potential surface for indirect prompt injection if those resources contain malicious instructions.
Ingestion points: Data is ingested from external sources via resources like courses, announcements, and userProfiles in the SKILL.md file.
Boundary markers: None explicitly defined in this file, though it references a shared skill for security rules.
Capability inventory: The skill facilitates extensive file-write and resource modification capabilities through methods like create, patch, and update across multiple resources.
Sanitization: No specific sanitization or filtering logic is documented for the data retrieved from the API.

gws-classroom