magento-di
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches development guidelines and configuration references from Adobe's official developer documentation portal (developer.adobe.com). This is a well-known, trusted source.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for potential indirect prompt injection because it ingests untrusted data from the web and has access to powerful tools.
- Ingestion points: Web search results and external documentation pages retrieved using the WebSearch and WebFetch tools (SKILL.md).
- Boundary markers: None identified; the skill does not provide specific delimiters or instructions to treat fetched data as untrusted.
- Capability inventory: The skill is permitted to use the Write, Edit, and Bash tools, which could allow for the execution of malicious instructions if they are ingested from external sources.
- Sanitization: No validation or sanitization mechanisms are defined for the content processed from the web.
Audit Metadata