xlsx-generator

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external XLSX templates and JSON specifications, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through scripts/analyze-template.ts, which extracts cell values and formulas from existing XLSX files, and scripts/generate-from-template.ts, which reads both XLSX content and JSON replacement specifications.
  • Boundary markers: The skill documentation and scripts do not implement explicit delimiters or boundary markers to distinguish between spreadsheet data and potential instructions for the agent.
  • Capability inventory: The skill enables the agent to read and write local files via Deno scripts with --allow-read and --allow-write permissions.
  • Sanitization: No sanitization or validation is applied to the content of spreadsheet cells or JSON data fields before they are processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the 'xlsx' library, which is downloaded from the well-known and official NPM package registry at runtime by the Deno environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:07 PM
Security Audit — agent-trust-hub — xlsx-generator