uno-platform
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by analyzing and modifying project files, which inherently exposes the agent to instructions that may be embedded in the codebase.\n
- Ingestion points: The agent is directed to inspect the repository context and targeted files to provide guidance (SKILL.md).\n
- Boundary markers: The instructions do not define clear boundaries or provide warnings to ignore instructions found within the code being analyzed.\n
- Capability inventory: The skill allows the agent to edit files and run build, test, and lint commands (SKILL.md).\n
- Sanitization: There are no mentioned processes for sanitizing data retrieved from the repository before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill allows the execution of build and validation commands. These are legitimate developer tools but represent a high-privilege surface that could be targeted by malicious project configuration.
Audit Metadata