The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
Ingestion points: The gws keep notes list and gws keep notes get commands retrieve note content from Google Keep, which is then processed by the agent.
Boundary markers: There are no explicit delimiters or instructions within this skill to treat note content as untrusted data or to ignore embedded instructions.
Capability inventory: The skill possesses capabilities to create, delete, and modify notes, as well as manage permissions via gws keep commands, which could be abused if an injection is successful.
Sanitization: The skill does not define any specific sanitization or filtering logic for the content retrieved from notes.

gws-keep