skills/garethmanning/education-agent-skills/argument-structure-scaffold-generator/Gen Agent Trust Hub
argument-structure-scaffold-generator
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions directly interpolate user-provided data into the prompt, creating a surface for indirect prompt injection attacks.
- Ingestion points: User-provided values for
argument_topic,student_level,scaffold_type, and other input fields are inserted directly into the core instructions inSKILL.md. - Boundary markers: No delimiters or isolation techniques (such as XML tags or triple backticks) are used to separate user input from the system's instructions.
- Capability inventory: The skill does not utilize any tools, file system access, or network operations, significantly mitigating the potential impact of an injection.
- Sanitization: The instructions do not include any validation or escaping mechanisms for the interpolated user content.
Audit Metadata