apps-script-utils

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes a shell script, scripts/check-latest-version.sh, which retrieves version information from the official npm registry at registry.npmjs.org. This is a standard maintenance operation targeting a well-known service.
  • [COMMAND_EXECUTION]: The skill executes local shell and Python commands to perform version comparison and output formatting. These operations use safe parsing methods (json.load) on retrieved data and do not execute remote code.
  • [INDIRECT_PROMPT_INJECTION]: The library provides several functions that define a data ingestion surface for the agent.
  • Ingestion points: Functions documented in SKILL.md and references/api-reference.md such as parseJson, decodeHtml, parseA1Notation, and various guards (isEmail, requireNonEmptyString) ingest external data.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: The skill includes scripts/check-latest-version.sh which utilizes curl for network requests and python3 for processing.
  • Sanitization: The skill provides its own sanitization and validation utilities, including escapeHtml, escapeXml, and the requireX assertion pattern to enforce input constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 11:47 AM
Security Audit — agent-trust-hub — apps-script-utils