content-scoring
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): The skill contains standard instructional logic for content evaluation without any attempts to subvert AI safety guidelines or bypass system prompts.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file paths, or network operations were identified.
- Code Execution (SAFE): No executable scripts or package dependencies are referenced; the skill consists solely of natural language instructions.
- Indirect Prompt Injection (SAFE): 1. Ingestion points: Processes user-provided text for scoring. 2. Boundary markers: None specified. 3. Capability inventory: None (no tools or scripts). 4. Sanitization: None. Because the skill lacks any executable capabilities, the data ingestion surface is not exploitable.
Audit Metadata