Skills
Navigate
skills/ortus-boxlang/skills/boxlang-modules-and-packages/Gen Agent Trust Hub

boxlang-modules-and-packages

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of BoxLang modules such as bx-redis, bx-pdf, and bx-csv from the official ForgeBox registry using the box CLI.
  • [COMMAND_EXECUTION]: Provides examples for utilizing the CommandBox box CLI to install, configure, and list modules within the BoxLang environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes functions that process external data files, creating a potential surface for indirect prompt injection.
  • Ingestion points: Functions csvParse and spreadsheetRead ingest data from local files such as data.csv and data.xlsx as documented in SKILL.md.
  • Boundary markers: No specific markers, delimiters, or safety instructions for handling untrusted data are provided in the documentation examples.
  • Capability inventory: The skill enables operations including file writing (fileWrite, spreadsheetWrite), network requests via LDAP (bx:ldap), and Redis caching (RedisService).
  • Sanitization: Implementation relies on standard language library functions; no additional content sanitization or validation is demonstrated in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:01 AM
Security Audit — agent-trust-hub — boxlang-modules-and-packages