landing-page-audit
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a surface for instructions embedded in audited content to influence agent behavior.\n
- Ingestion points: The skill ingests data from a user-supplied
Landing page URL(web content) andAd copy or emailtext as described in theInput Requiredsection ofSKILL.md.\n - Boundary markers: The instructions lack explicit delimiters or safety prompts to ensure the agent ignores instructions found within the audited landing page content.\n
- Capability inventory: The skill reads local files containing brand profiles, compliance rules, custom templates, and agency SOPs located in
~/.claude-marketing/andskills/context-engine/(documented in theProcesssection ofSKILL.md).\n - Sanitization: No sanitization or validation logic is defined to filter malicious patterns from the external landing page content or ad copy before analysis.
Audit Metadata