shader-programming

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill suggests using glslangValidator and naga to validate shader source files. These are standard developer tools used for the skill's primary purpose, and their inclusion is consistent with best practices for shader development.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it involves processing user-provided shader code.\n
  • Ingestion points: Shader source files (.frag, .wgsl) referenced in the validation steps in SKILL.md.\n
  • Boundary markers: Absent; there are no specific delimiters or warnings to ignore instructions within the shader code.\n
  • Capability inventory: Capability to execute shell-based validation tools (glslangValidator, naga) on the provided files.\n
  • Sanitization: Absent; the skill does not specify any sanitization or validation of the file paths or content beyond the use of the mentioned tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 09:53 PM