enhance-prompt
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest raw user prompts and instruct the agent to execute the enhanced versions directly. This pattern creates a surface for indirect prompt injection where malicious instructions in the input could be amplified or executed. \n
- Ingestion points: User-provided raw prompts processed in SKILL.md. \n
- Boundary markers: No specific delimiters or safety instructions are used to isolate the user-provided input. \n
- Capability inventory: The skill utilizes various platform-specific interactive tools (e.g., AskUserQuestion, ask_user) and directs the agent to execute the resulting prompt. \n
- Sanitization: There is no evidence of validation or filtering applied to the user input before processing.
Audit Metadata