architecture-doc-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language requests from users and possesses capabilities to execute arbitrary shell commands and write files. This combination creates an attack surface where an adversary could provide data containing hidden instructions that the agent might execute with its granted permissions.
Audit Metadata