wcag-audit-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides examples for using accessibility audit tools via the command line, including
@axe-core/cli,pa11y, andlighthouse. These are standard, well-known tools for web accessibility verification and are used as intended for the skill's primary purpose. - [INDIRECT_PROMPT_INJECTION]: The skill describes processes for auditing external web content, which introduces a potential surface for indirect prompt injection if an attacker-controlled page contains malicious instructions meant to influence the agent.
- Ingestion points: The
runAccessibilityAuditfunction (SKILL.md) and CLI commands allow for the processing of external webpages. - Boundary markers: None present; the instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the audited content.
- Capability inventory: The skill uses
page.evaluatefor browser-based JavaScript execution and shell commands for auditing, providing a mechanism where poisoned content could potentially trigger unexpected tool behavior. - Sanitization: No specific sanitization or filtering of the external page content is defined before the audit analysis.
Audit Metadata