architecture
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from the repository being analyzed, creating a potential surface for indirect prompt injection.
- Ingestion points: The instructions direct the agent to read repository-specific files such as
AGENTS.mdandCONTEXT.md, and to perform structural surveys of the directory tree. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the content of these external files as untrusted or to ignore embedded instructions.
- Capability inventory: The skill is designed to guide refactoring and structural changes, which involves the use of file system tools (read/write) and version control commands.
- Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content of the files it processes.
Audit Metadata