bx-sites-content-quality

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the bxSites and boxlang CLI tools to perform project-specific tasks such as linting Markdown files, listing blog drafts, and querying search indices. These operations are standard for a static site generator toolset.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of Markdown files and frontmatter content from the local project.
  • Ingestion points: The agent reads raw Markdown source files from the docs/ and docs/blog/posts/** directories.
  • Boundary markers: The instructions do not specify explicit delimiters for the content being linted or searched.
  • Capability inventory: The skill utilizes shell command execution to run the bxSites tool suite.
  • Sanitization: The skill relies on the validation logic within the bxSites CLI tool to handle heading structures and date formats in Markdown frontmatter.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 03:15 AM
Security Audit — agent-trust-hub — bx-sites-content-quality