44-webgl
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze existing repositories and user-provided constraints, creating a potential entry point for malicious instructions embedded in project files or documentation.\n
- Ingestion points: The implementation contract in
SKILL.mddirects the agent to inspect the existing repository, framework, and dependencies.\n - Boundary markers: The instructions lack specific delimiters or warnings to treat repository content as untrusted data rather than instructions.\n
- Capability inventory: The skill grants the agent authority to generate production-quality WebGL logic and manage GPU/media resources, which could be misused if influenced by injected prompts.\n
- Sanitization: No protocols are defined for the agent to filter or validate content ingested from external source code or requirements documents.
Audit Metadata