schedule
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to drive its autonomous scheduling logic. Category: Indirect Prompt Injection -> Attack Vector: 8b (Multi-step chains)
- The skill reads backlog items and plan files to generate task orders -> Capability: High (Autonomous scheduling and task definition) -> Sanitization: Absent (No evidence of input validation or content filtering for plan files).
Audit Metadata