enhance-prompt
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is designed for prompt engineering and operates exclusively on text. It contains no malicious code or behaviors.\n- [NO_CODE]: No executable scripts or code files are present in the skill package.\n- [PROMPT_INJECTION]: The skill handles user input which could be used for indirect prompt injection. However, the requirement for human review of the output is a strong mitigation.\n
- Ingestion points: User input provided via the
raw_inputparameter inSKILL.md.\n - Boundary markers: The skill does not use explicit delimiters to isolate user input in its output templates.\n
- Capability inventory: No dangerous tools, commands, or code execution capabilities were found.\n
- Sanitization: The skill is designed to preserve the original user input to maintain intent, rather than sanitizing it.
Audit Metadata