bx-docbox
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for executing documentation generation via CLI tools such as
boxlang module:docboxandbox docbox generate. These commands are standard for the BoxLang and CommandBox ecosystem and are used for their intended purpose of generating project documentation. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process source code annotations (untrusted data) to generate output. This presents a potential surface for indirect prompt injection if the source code contains malicious instructions intended for the agent.
- Ingestion points: Source code directories specified in the
sourceparameter across CLI and programmatic examples (e.g.,SKILL.md). - Boundary markers: None explicitly defined in the skill instructions to separate project data from documentation generator instructions.
- Capability inventory: The skill facilitates writing files to the local file system via the
output-dirconfiguration. - Sanitization: The skill relies on the underlying DocBox library to handle and potentially escape source code annotations, though no specific sanitization steps are detailed in the instructions.
Audit Metadata