onboard
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands such as
mkdirandfindto explore the project directory and create metadata folders. These are standard utility commands for file system management.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the codebase to generate summaries, which could theoretically be influenced by malicious code comments.\n - Ingestion points: Scans source code and configuration files in the project directory.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided in the subagent's task definition.\n
- Capability inventory: Includes directory creation, file discovery, and writing YAML files.\n
- Sanitization: No explicit content filtering or sanitization is performed on the data read from project files.
Audit Metadata