Accessibility Testing
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of a markdown file (SKILL.md) and does not include any executable code, shell scripts, python modules, or configuration files that could be executed by an agent.
- [SAFE]: No malicious patterns, such as prompt injection, credential theft, or obfuscated content, were detected in the skill description or examples. The content is strictly limited to instructional material for web accessibility testing.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by instructing the agent to process untrusted data (URLs, HTML, and React components). However, the risk is mitigated by the lack of any executable scripts or tool-calling logic within the skill itself. 1. Ingestion points: Usage section (URLs, HTML blocks, components). 2. Boundary markers: Absent in instructions. 3. Capability inventory: No file-system, network, or subprocess capabilities provided in scripts. 4. Sanitization: Not mentioned in the workflow.
Audit Metadata