workflow-automation
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPERSISTENCEDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents patterns for event-driven workflows and AI orchestrators that process untrusted external data.
- Ingestion points: External data is ingested through event payloads (e.g.,
event.data.taskinaiOrchestrator,event.data.orderinprocessOrderwithin SKILL.md). - Boundary markers: Code examples do not demonstrate the use of delimiters or "ignore" instructions for processed data.
- Capability inventory: The skill describes workflows capable of external API calls (Stripe), email dispatch, and database queries.
- Sanitization: Examples do not include sanitization or validation logic for the ingested event data.
- [PERSISTENCE]: The skill provides instructions and examples for creating scheduled tasks using cron triggers (e.g.,
cron: "0 9 * * *"). This pattern allows for the periodic execution of workflows across sessions. - [DYNAMIC_EXECUTION]: The orchestrator-worker pattern utilizes dynamic dispatching where a central coordinator invokes specialized child workflows (
executeChild) based on the content of a task plan generated at runtime.
Audit Metadata