integrate-dialogue-narrative
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions proactively address security risks (OWASP ASI) by mandating sandboxed condition evaluation and forbidding the use of
eval()or reflection for command dispatch. - [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected.
- [SAFE]: External dependencies mentioned (Yarn Spinner, Ink) are industry-standard tools for narrative development.
- [INDIRECT_PROMPT_INJECTION]: The skill naturally interacts with external data (narrative files and localization tables) which represents a potential attack surface. However, the skill explicitly provides mitigation strategies, such as type-checking, sandboxing, and using a headless linter in CI to validate external content.
Audit Metadata