content-scoring
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, hidden instructions, or dangerous command executions were found. The skill operates entirely as a text-based evaluation framework.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content to generate scores. While this represents a data ingestion surface, the skill does not have access to any external tools, network resources, or sensitive file paths that could be exploited via injected instructions.
Audit Metadata