skills/garethmanning/education-agent-skills/intelligent-tutoring-dialogue-designer/Gen Agent Trust Hub
intelligent-tutoring-dialogue-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses template variables to insert user-controlled data directly into the system prompt, creating an attack surface for instruction override.
- Ingestion points: The
learning_objectiveandanticipated_difficultiesfields inSKILL.mdare directly interpolated into the primary task prompt. - Boundary markers: The prompt fails to use delimiters (e.g., triple quotes, XML tags) or specific instructions to isolate these inputs from the system instructions.
- Capability inventory: The skill does not request or use high-risk tools (no shell access, no file system writes, no network requests), limiting the potential impact of an injection.
- Sanitization: There is no evidence of input validation, character escaping, or filtering for the user-supplied strings.
Audit Metadata