magento-catalog
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to fetch external data from the Adobe Developer portal to guide feature implementation.
- Ingestion points: SKILL.md specifies fetching documentation via WebFetch from developer.adobe.com.
- Boundary markers: The skill does not provide delimiters or instructions to ignore potential commands within the fetched external content.
- Capability inventory: The skill utilizes Bash, Write, and Edit tools, allowing for file system modification and command execution based on context.
- Sanitization: There is no evidence of sanitization or validation logic for the content retrieved from the external URLs.- [EXTERNAL_DOWNLOADS]: Fetches development components and indexing guides from Adobe's official developer portal.
Audit Metadata