dev-kit-research
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill provides the agent with the authority to 'run small commands or scripts' to verify technology behavior. While scoped to research, this provides a mechanism for arbitrary command execution.
- [Indirect Prompt Injection] (LOW): The skill reads from untrusted sources such as web search results and external tickets without explicit boundary markers or sanitization, potentially allowing external instructions to influence the command execution phase. 1. Ingestion points: .dev-kit/tickets/ and web search queries. 2. Boundary markers: Absent. 3. Capability inventory: Command execution and file system access. 4. Sanitization: None.
Audit Metadata