effect-typescript

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of the effect-solutions CLI tool globally using the Bun package manager.
  • [COMMAND_EXECUTION]: Instructs the agent to execute shell commands for package management (bun install), testing (bun test), and repository maintenance (git submodule update).
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on and generates TypeScript source code and configuration files, which represents an attack surface for instructions embedded in external files to influence the agent.
  • Ingestion points: Processes TypeScript source files, config/*.json configuration files, and .sops.json encrypted secret files.
  • Boundary markers: None identified; the instructions do not specify the use of delimiters or 'ignore' instructions for external content.
  • Capability inventory: The skill possesses the ability to execute shell commands via Bun/Git and manage infrastructure resources through Alchemy.
  • Sanitization: Employs schema-based validation (Schema.fromJsonString) for JSON data parsing, but lacks specific sanitization for arbitrary TypeScript code manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:51 AM
Security Audit — agent-trust-hub — effect-typescript