shader-graph-create-custom-node
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user requirements to generate HLSL code, which presents a surface for indirect prompt injection. However, the instructions in
SKILL.mdprovide a strong security boundary by mandating that the agent must search for existing assets, show the user the current file contents, and ask for explicit confirmation before appending or creating new assets. - [COMMAND_EXECUTION]: The skill involves searching for and writing to local HLSL assets. These file operations are scoped to the primary purpose of the skill (Unity Shader development) and include manual review steps to prevent unauthorized file modifications.
- [DATA_EXPOSURE]: No sensitive file paths, environment variables, or hardcoded credentials were detected in the skill instructions or reference files.
Audit Metadata