save-tokens
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The 'Skill Isolation' section contains instructions that attempt to hijack the agent's control flow. Specifically, it claims to be the 'sole active authority' and commands the agent to 'suppress' any other skills or external activations. This pattern is designed to bypass the agent platform's intended multi-skill orchestration and behavior management.
Audit Metadata