cs-marketing-website
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect external websites and conversion paths, which introduces a surface for indirect prompt injection from untrusted web content.
- Ingestion points: Website inspection, routes, and sitemap analysis in Step 1.
- Boundary markers: Absent. The instructions do not specify delimiters or instructions to ignore embedded commands for web content.
- Capability inventory: Writing records to the client repository or operating workspace (Step 4).
- Sanitization: Absent.
Audit Metadata