The Agent Skills Directory

[COMMAND_EXECUTION]: The skill interfaces with the wecom-cli binary to manage todos. It executes shell commands where input parameters are encapsulated in single-quoted JSON strings, a standard operational pattern for this toolset.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it retrieves and processes user-generated todo descriptions that could contain malicious instructions. 1. Ingestion points: Todo content retrieved via get_todo_detail in SKILL.md. 2. Boundary markers: No specific delimiters are used to wrap external content in the display instructions. 3. Capability inventory: Commands include create_todo, update_todo, and delete_todo in SKILL.md. 4. Sanitization: The instructions do not specify sanitization or validation for retrieved todo text.
[SAFE]: The skill includes safety-oriented instructions such as requiring explicit human confirmation before executing the delete_todo operation and ensuring user IDs are resolved to names via the wecomcli-contact skill to prevent ambiguity.

wecomcli-todo