reviewing-motoko

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill offers legitimate and high-quality instructional content for Motoko developers, establishing a structured approach to code audits and design reviews. It focuses on important safety concepts like invariant encoding and state persistence in the Internet Computer environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze external Motoko source code and configuration files, creating a surface for potential indirect prompt injection from the contents of those files.
  • Ingestion points: Motoko (.mo) source files and mops.toml configuration files are ingested into the agent's context for review.
  • Boundary markers: The instructions do not define specific delimiters or instructions to isolate untrusted code content from the agent's analysis logic.
  • Capability inventory: The skill utilizes the standard mops package manager for automated linting and formatting operations.
  • Sanitization: There is no explicit sanitization step for the ingested code before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill recommends executing mops check --fix, which is a standard utility in the Motoko ecosystem for code verification and formatting.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:54 PM
Security Audit — agent-trust-hub — reviewing-motoko