skills/jwynia/teach/xlsx-generator/Gen Agent Trust Hub

xlsx-generator

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface due to the processing of external, untrusted data.
  • Ingestion points: The scripts analyze-template.ts, generate-from-template.ts, and generate-scratch.ts read data from external XLSX templates and JSON specification files.
  • Boundary markers: The instructions lack delimiters or constraints to prevent the agent from following instructions embedded within the spreadsheet or JSON data.
  • Capability inventory: The Deno execution environment is granted --allow-read and --allow-write permissions, allowing the agent to modify the file system based on parsed input.
  • Sanitization: No sanitization or escaping mechanisms are present to handle malicious strings within the spreadsheet cells or JSON fields.
  • [EXTERNAL_DOWNLOADS]: The skill downloads external code from established registries.
  • It imports the xlsx@0.18.5 library from the NPM registry.
  • It references standard library components from the JSR registry (@std/cli, @std/path).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 09:45 AM