things-morning-organizer
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the 'Things' application to perform categorization, tagging, and prioritization. If todo titles or notes contain malicious instructions, they could potentially influence how the agent processes tasks.
- Ingestion points: Data is pulled from the Things app via tools such as
things_get_today,things_get_inbox,things_get_anytime,things_get_upcoming, andthings_get_somedayinSKILL.md. - Boundary markers: The skill instructions do not specify the use of clear delimiters or 'ignore embedded instructions' warnings when processing the todo content.
- Capability inventory: The skill has the ability to write to the user's task list using
things_update_todoandthings_add_todo. - Sanitization: There is no evidence of content sanitization or filtering beyond a directive to 'be conservative' when tagging items.
Audit Metadata