content-audit
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches published AEM EDS pages and their HTML fragments to perform structural and performance audits. This behavior is documented and core to the skill's purpose.
- [PROMPT_INJECTION]: The skill processes untrusted external HTML, creating a surface for indirect prompt injection.
- Ingestion points: SKILL.md Step 1 fetches content from user-provided URLs and associated fragments (.plain.html, nav.plain.html, footer.plain.html).
- Boundary markers: Includes an 'External Content Safety' section that explicitly defines boundaries for fetching and handling external data.
- Capability inventory: Uses network fetch capabilities to retrieve remote HTML content for parsing.
- Sanitization: Specific instructions command the agent to treat content as untrusted and strictly avoid executing scripts or interpreting dynamic content.
Audit Metadata