od-new-generation
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected in the skill instructions or associated files. The skill correctly implements a generation scenario using a structured pipeline.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-defined inputs for
artifactKind,audience, andtopic, which are interpolated into the prompt query. This represents a standard surface for indirect prompt injection common to generative AI tools. - Ingestion points: Input variables in
open-design.json. - Boundary markers: None defined in the query template.
- Capability inventory: The
generatestage utilizes thefile-writeatom. - Sanitization: No input filtering or validation is specified.
Audit Metadata