skills/guoxiangjie/skills/prd-suite/Gen Agent Trust Hub

prd-suite

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes user-controlled data from requirement templates and XMind files to generate documentation.\n
  • Ingestion points: Untrusted data enters the context through requirement_template.md (read via parser.js) and .xmind files (read via XMind MCP tools).\n
  • Boundary markers: The skill employs specific markdown headers and structured templates (e.g., templates/main_prd_template.md) to isolate and format extracted data, though it lacks explicit 'ignore instructions' delimiters for the ingested content.\n
  • Capability inventory: The skill has the capability to write to the file system (fs.writeFileSync in scripts/utils.js) and call XMind parsing tools.\n
  • Sanitization: Content extraction is performed using regex patterns in scripts/parser.js, providing basic structural validation.\n- [COMMAND_EXECUTION]: The skill includes JavaScript utility scripts (scripts/utils.js, scripts/parser.js, scripts/level_analyzer.js) that use standard Node.js modules like fs and path to manage PRD files and configuration. These operations are restricted to the local project directories and are consistent with the skill's documented purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:03 AM
Security Audit — agent-trust-hub — prd-suite