makepad-shaders
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and process data from external files to provide answers, which represents an attack surface for indirect prompt injection.
- Ingestion points: The skill reads
./references/shader-basics.mdand./references/sdf2d-reference.mdinto the agent context in SKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions found within these reference files.
- Capability inventory: No dangerous capabilities such as network operations, arbitrary command execution, or file writing are enabled or used within the skill.
- Sanitization: There is no evidence of sanitization or validation performed on the content of the reference files before processing.
Audit Metadata