doc-brd-audit

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill orchestrates the execution of internal scripts doc-brd-validator and doc-brd-reviewer as part of its documented workflow to perform structural and quality audits on BRD files.\n- [PROMPT_INJECTION]: The skill processes user-provided markdown files, creating a surface for indirect prompt injection.\n
  • Ingestion points: Reads content from Business Requirement Documents located in the docs/01_BRD/ directory.\n
  • Boundary markers: No specific delimiters or instructions are specified to separate untrusted document content from the skill's logic.\n
  • Capability inventory: The skill writes audit reports to the filesystem and initiates downstream processing via doc-brd-fixer.\n
  • Sanitization: No evidence of content sanitization or validation of input markdown content is provided before it is processed by the audit logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:04 PM