pro-report-builder

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's CSS framework fetches font assets and stylesheets from Fontshare (api.fontshare.com), a well-known typography service.
  • [COMMAND_EXECUTION]: The skill provides the agent with specific shell commands to execute Google Chrome in headless mode for the purpose of printing generated HTML documents to PDF.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data (metrics, raw numbers, spreadsheets) to populate report components, which creates a potential surface for indirect injection if the source data is untrusted.
  • Ingestion points: User-provided data, API exports, and spreadsheets (referenced in SKILL.md).
  • Boundary markers: None explicitly mentioned in the instructions to separate data from the document structure.
  • Capability inventory: Generates standalone HTML files and uses shell commands to interact with the file system and browser (SKILL.md).
  • Sanitization: The instructions do not explicitly detail sanitization or escaping of the user-provided data before it is interpolated into the HTML output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:54 PM
Security Audit — agent-trust-hub — pro-report-builder