aria-command-name
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides purely instructional content for performing accessibility reviews on HTML command elements. Analysis of all scripts and instructions reveals no evidence of malicious intent, data exfiltration, or unauthorized command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze external HTML and interactive components, which inherently creates an indirect prompt injection surface. A malicious user or external source could theoretically embed instructions within the markup being reviewed. However, the skill lacks any capabilities (such as network operations, file writing, or shell execution) to act upon such instructions, and this risk is considered a standard characteristic of its intended purpose.
- Ingestion points: Analyzes rendered HTML and interactive design-system patterns (SKILL.md).
- Boundary markers: None provided within the skill instructions.
- Capability inventory: No tool usage, network operations, or file system modifications are requested or implemented.
- Sanitization: None specified for input markup.
- [NO_CODE]: The skill contains no executable scripts (e.g., Python, Node.js, Shell). It relies entirely on natural language instructions for the agent, which significantly limits the potential for technical exploitation or privilege escalation.
Audit Metadata