ecommerce-email-marketing-builder
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes installation instructions using
npxto fetch content from the repositorynexscope-ai/eCommerce-Skills. It also contains links to the vendor's website and GitHub repository. These external references trace back to the verified skill author, Nexscope.\n- [INDIRECT_PROMPT_INJECTION]: The skill prompts users to provide competitor URLs for reference during the creation of marketing flows. This presents a surface for indirect prompt injection if the agent attempts to fetch and process content from these untrusted external locations.\n - Ingestion points: The follow-up questionnaire in
SKILL.md(Step 2, Question 7) specifically requests 'Competitors to reference? (names or URLs, or skip)'.\n - Boundary markers: The instructions lack explicit delimiters or instructions to the agent to ignore potential commands embedded within the retrieved competitor data.\n
- Capability inventory: The skill's primary functions involve generating text-based marketing copy, sequence diagrams, and ESP setup instructions; it does not contain instructions for sensitive file system modification or network exfiltration.\n
- Sanitization: No logic is provided to sanitize or validate the content retrieved from external competitor URLs.
Audit Metadata