The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of a local binary gws to perform all Classroom operations. It facilitates subprocess calls to this tool for resources like courses, invitations, and user profiles.
[INDIRECT_PROMPT_INJECTION]: The skill provides an interface to ingest and process data from Google Classroom, which is an untrusted external source.
Ingestion points: Data is ingested through methods such as courses.list, courses.get, announcements.list, and posts.get via the gws tool (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the retrieved Classroom data.
Capability inventory: The skill has significant write capabilities including courses.delete, invitations.create, and courses.patch, which could be targeted by an injection attack.
Sanitization: There is no evidence of validation or sanitization of the content retrieved from the Classroom API before it is processed by the agent.

gws-classroom