roadmap
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious patterns, obfuscation, or unauthorized data access commands were detected in the skill instructions.
- [Indirect Prompt Injection] (LOW): The skill interpolates untrusted user input (e.g., tenant_name, decision_context) directly into a template without boundary markers or sanitization. However, because the skill lacks any dangerous capabilities like command execution or network access, the impact is limited to influencing the content of the generated text memo.
- [NO_CODE] (SAFE): This skill contains only natural language instructions and templates with no executable scripts or external dependencies.
Audit Metadata