brandfy-guia-pdf
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes external binaries pandoc and weasyprint via a Node.js script to transform Markdown into PDF. This is the primary function and is implemented safely using argument arrays to prevent shell injection.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from BRAND.md to populate PDF metadata and content. * Ingestion points: The file BRAND.md is read by scripts/build-brand-guide.mjs. * Boundary markers: No explicit markers or delimiters are used for the ingested data. * Capability inventory: File system access and subprocess execution via scripts/build-brand-guide.mjs. * Sanitization: Content is extracted via regular expressions; command execution is handled safely via spawnSync.
Audit Metadata