The Agent Skills Directory

[SAFE]: The skill provides a set of instructions for using the gws CLI to interact with Google Keep API resources. This is standard functionality for a productivity-oriented AI agent skill.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes external content from Google Keep notes.
Ingestion points: Data enters the context via the get, list, and media download methods described in SKILL.md.
Boundary markers: The instructions do not define delimiters or directives to ignore instructions embedded in the note content.
Capability inventory: The agent has the ability to execute shell commands via the gws binary.
Sanitization: There is no specified sanitization or validation of the retrieved note data or media content.

gws-keep