schedule
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it ingests and processes session history to create prompts for future autonomous execution.
- Ingestion points: The skill is instructed to "Review the session history to identify the core task" and distill it into a prompt (SKILL.md).
- Boundary markers: No specific delimiters or boundary markers are defined to isolate the distilled task data from the agent's instructions.
- Capability inventory: The skill utilizes the
create_scheduled_tasktool to enable future autonomous execution of the generated prompt (SKILL.md). - Sanitization: No sanitization or validation of the session history is performed before the distillation process.
Audit Metadata