aria-required-children
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to review and analyze rendered markup and interactive states, creating a potential surface for indirect prompt injection if the audited content contains hidden instructions. \n
- Ingestion points: Analyzes rendered markup and interactive states as specified in SKILL.md. \n
- Boundary markers: No delimiters or specific instructions to ignore embedded content are provided. \n
- Capability inventory: The skill is restricted to analytical tasks and does not possess capabilities for file modification, network communication, or shell command execution. \n
- Sanitization: The instructions do not define methods for sanitizing or validating the input markup.
Audit Metadata