summary-generator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill contains no executable scripts, shell commands, or dependency files. It is strictly a prompt-based instruction set.
- [DATA_EXPOSURE] (SAFE): No sensitive file paths or hardcoded credentials detected.
- [PROMPT_INJECTION] (SAFE): No adversarial or bypass instructions found.
- [Indirect Prompt Injection] (INFO): The skill processes external text (articles, notes). While it lacks delimiters to prevent 'ignore previous instructions' attacks within the source text, it possesses no dangerous capabilities to exploit.
Audit Metadata