gtd
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input to manage task lists, creating a surface for indirect prompt injection.
- Ingestion points: User-provided open loops and commitments enter the agent context through conversation and the
--captureargument. - Boundary markers: While items are processed individually, the prompt does not require specific delimiters like triple quotes or JSON envelopes for the interpolated data.
- Capability inventory: The skill utilizes local file-system tools to read and write its state file,
gtd-state.json, but lacks network access or arbitrary command execution capabilities. - Sanitization: The skill includes a specific defensive instruction to disregard embedded task instructions that attempt to redirect the workflow.
Audit Metadata