pixi-vn-ink-input
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of user-provided data into the story narration, which is a common surface for indirect prompt injection if that narration is subsequently processed by an AI agent.
- Ingestion points: Untrusted user input is requested and captured via the
# request inputhashtag command inSKILL.md. - Boundary markers: No specific technical delimiters are enforced within the provided Ink examples, though the text is clearly separated.
- Capability inventory: The skill is primarily instructional and does not include scripts with subprocess, file-write, or network capabilities.
- Sanitization: The documentation includes a clear security warning to treat submitted values as untrusted player content and advises that the UI should apply appropriate validation or escaping.
Audit Metadata