accessibility
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses command-line tools such as
npx lighthouseandaxeto perform audits on user-specified URLs. - [EXTERNAL_DOWNLOADS]: Fetches auditing packages from the official NPM registry, including Google's
lighthouseand Deque Systems'@axe-core/cli. - [PROMPT_INJECTION]:
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web content from external URLs, which could contain malicious instructions designed to influence the agent's behavior during the audit process.
- Ingestion points: Content from external URLs is processed via the
lighthouseandaxecommands inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded text are used when processing the external content.
- Capability inventory: The skill possesses the ability to execute shell commands (
npx,axe) and potentially write audit results to the file system. - Sanitization: No sanitization of the external content is performed within the skill before processing.
Audit Metadata