marketing-analytics
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the agent-browser tool from the vercel-labs GitHub organization. This is a trusted source used for performing live performance and SEO audits as part of the analytics specialist workflow.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) during its audit phase.
- Ingestion points: Data from external websites is ingested via agent-browser get text body in SKILL.md.
- Boundary markers: Absent; there are no specific markers to delineate untrusted web content from instructions.
- Capability inventory: The skill can execute JavaScript in the browser (agent-browser eval) and write files to the brand's local directory.
- Sanitization: Absent; retrieved web content is processed without filtering.
Audit Metadata