give-me-tips
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the host environment by executing shell commands such as
omo --list-tipsorsenpi --list-tips. It also provides instructions to use theOMO_BINenvironment variable to locate the executable, facilitating interaction with the vendor's command-line tools.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from various ingestion points which could theoretically contain malicious instructions. \n - Ingestion points: Retrieve data from
omo --list-tipscommand output, localsettings.jsonfiles, and source code files within the@code-yeongyu/senpiandcode-yeongyu/oh-my-openagentrepositories.\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the external code or configuration files being read.\n
- Capability inventory: The skill utilizes file reading and shell command execution capabilities to gather information.\n
- Sanitization: Content retrieved from the file system or command output is processed without explicit sanitization steps defined in the skill instructions.
Audit Metadata