29-video-scroll-scrubbing
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 ingest repository content and user requirements to implement frontend code, establishing an indirect prompt injection surface.\n
- Ingestion points: SKILL.md (instructions to inspect the existing repository, framework, dependencies, and conventions).\n
- Boundary markers: The skill does not define specific delimiters or boundary markers for content read from the repository.\n
- Capability inventory: The agent is empowered to generate, modify, and optimize production-quality frontend code, including handling media and GPU resources.\n
- Sanitization: No specific sanitization or validation logic is defined for the repository data being processed.
Audit Metadata