planning-wcag-audit
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches untrusted data from external sources to compile a list of pages for audit planning.
- Ingestion points: The skill uses
WebFetchto retrievesitemap.xmland crawl internal links from user-supplied website URLs as described inSKILL.mdandpage-selection-guide.md. - Boundary markers: The instructions do not include specific delimiters or 'ignore' directives to prevent the agent from being influenced by instructions embedded in the external content.
- Capability inventory: The skill utilizes
WebFetchfor network access andWriteto save the audit plan, allowing untrusted data to influence file content. - Sanitization: There is no evidence of URL filtering or content sanitization before the agent processes and includes fetched data in the final report.
Audit Metadata