The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires and executes a local binary named gws to interact with the Google Tasks API. Command discovery is performed through gws tasks --help and gws schema.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external content from Google Tasks that could contain malicious instructions.
Ingestion points: Task content retrieved via gws tasks tasks list and gws tasks tasks get in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between task data and control instructions.
Capability inventory: The agent can modify or delete data using delete, insert, patch, and update methods described in SKILL.md.
Sanitization: There is no evidence of input validation or sanitization of the retrieved task content before it is processed by the agent.

gws-tasks