web-interface-conventions
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest and act upon external design specifications and task requirements, which constitutes a potential indirect prompt injection surface.\n
- Ingestion points: External design sources and task references identified in
SKILL.mdandreferences/design-sources.md.\n - Boundary markers: No specific delimiters are defined in the instructions to isolate user-provided design content from the agent's instructions.\n
- Capability inventory: The skill authorizes the agent to modify HTML, CSS, and interaction logic across the project's source files.\n
- Sanitization: No specific sanitization or validation logic is prescribed for the content of the design references.
Audit Metadata