responsive-review
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely instructional content for performing accessibility audits across different viewports, zoom levels, orientations, and font sizes.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review external web interfaces. This creates a potential surface for indirect prompt injection if the content being analyzed contains instructions intended to influence the agent. However, no specific dangerous capabilities (such as network exfiltration or file writing) are invoked by this skill, making the risk negligible.
- Ingestion points: Web interface content being reviewed during the process steps (SKILL.md).
- Boundary markers: None provided within the instructions.
- Capability inventory: None detected in this file; the skill focuses on documenting and reporting issues.
- Sanitization: None provided.
Audit Metadata