magento-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data which constitutes an attack surface for indirect prompt injection.\n
- Ingestion points: Retrieves live documentation from experienceleague.adobe.com and performs web searches for deployment strategies via WebSearch and WebFetch tools.\n
- Boundary markers: The instructions lack specified delimiters or explicit instructions for the agent to treat external content as untrusted or to ignore potentially embedded instructions.\n
- Capability inventory: The skill utilizes Bash, Write, and Edit tools, which allow the agent to execute shell commands and modify files based on its interpreted context.\n
- Sanitization: No mechanisms for sanitizing, filtering, or validating external content are defined before the agent processes the retrieved information.
Audit Metadata