aiui-docs
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The agent is instructed to run the shell command
git diff --checkfrom the repository root to validate changes and identify whitespace errors before finishing. - [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external documentation files which are outside its own instruction set, creating an attack surface for embedded malicious instructions. * Ingestion points: Repository-local files under the
documentation/directory and thedocumentation/toc.jsonfile. * Boundary markers: The instructions do not specify any delimiters or safety markers to isolate potentially malicious data in the documentation files from the agent's instructions. * Capability inventory: The agent has the ability to read and write files within the repository and execute git commands. * Sanitization: No mechanisms for sanitizing or escaping the content of the documentation files are described.
Audit Metadata