tabs-accessibility
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code, templates, and rendered HTML, which creates an indirect prompt injection vulnerability surface. If an attacker provides markup containing hidden instructions, the agent might inadvertently follow them during the review process.
- Ingestion points: Markup templates, server-rendered HTML, and shared component source code analyzed by the agent, as specified in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers to isolate the analyzed content from the agent's core instructions.
- Capability inventory: The skill instructions are limited to code review and identifying violations; no high-privilege capabilities like file-system writes or network operations are requested.
- Sanitization: There is no evidence of sanitization or filtering logic applied to the external content before it is processed by the agent.
Audit Metadata