bx-ini
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the user to execute shell commands (
install-bx-module bx-iniandbox install bx-ini) to install the required module. These are standard package management operations within the BoxLang environment. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the reading of data from external INI files, which presents a surface where untrusted configuration data could influence the agent's behavior.
- Ingestion points: Data is loaded from local files using
getProfileString,getProfileSection, andgetProfileSectionsas demonstrated inSKILL.md. - Boundary markers: Absent; the instructions do not include delimiters or warnings to treat the content of INI files as potentially untrusted data.
- Capability inventory: The skill includes file-writing and deletion capabilities via
setProfileString,removeProfileSection, andremoveProfileStringfunctions. - Sanitization: Absent; the skill does not describe any validation or sanitization logic for the data retrieved from the configuration files before it is used by the agent.
Audit Metadata