bx-sites-content-quality
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
bxSites(orboxlang bxSites) command-line interface to perform content checks. These commands are project-specific utilities for the ortus-boxlang/bx-sites ecosystem and do not exhibit malicious behavior. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from local Markdown files (
docs/) and search indices (site/search-index.json). While this creates a potential surface for indirect prompt injection if those files contain adversarial instructions, the tool's capabilities are restricted to content validation and filtering. - Ingestion points: Markdown source files in the
docs/directory and the generatedsite/search-index.jsonfile. - Boundary markers: None specified in the instructions.
- Capability inventory: Execution of local
bxSitesCLI verbs (lint, blog:drafts, blog:find, search:query) as documented in SKILL.md. - Sanitization: No explicit sanitization of document content is mentioned before it is processed by the CLI tools.
Audit Metadata