shan-ze-school
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted user input directly into its prompt construction workflow without isolation or sanitization.
- Ingestion points: The skill accepts user-supplied descriptions via the
[SUBJECT]placeholder in theSKILL.mdtemplate. - Boundary markers: There are no delimiters (e.g., triple backticks or XML tags) or explicit instructions used to isolate the user input from the skill's operational logic.
- Capability inventory: The skill generates complex prompts and interacts with image generation tools when available.
- Sanitization: The skill does not perform validation, filtering, or escaping of the user-provided subject before processing.
Audit Metadata