reviewing-motoko

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use mops check --fix for automated code formatting and style checks. This is a standard developer tool within the Motoko ecosystem and is used here for its intended purpose of code maintenance.
  • [INDIRECT_PROMPT_INJECTION]: As an auditing skill, it is designed to process untrusted Motoko source files. While such files could contain adversarial instructions, the skill's detailed methodology and severity-ranked finding system provide a structured analysis process that mitigates the risk of the agent deviating from its primary task.
  • Ingestion points: Reads .mo files, mops.toml, and migration files.
  • Boundary markers: The skill defines a strict order of operations and specific design criteria to guide the agent's analysis.
  • Capability inventory: The agent can perform shell execution (mops check --fix) and provide structured feedback.
  • Sanitization: The skill encourages using automated tools which apply standardized rules, reducing reliance on manual interpretation of code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 06:12 PM
Security Audit — agent-trust-hub — reviewing-motoko