skills/caffeinelabs/skills/mops-cli/Gen Agent Trust Hub

mops-cli

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the mops CLI to download project dependencies from a package registry and GitHub (e.g., mops add org/repo). It also manages the toolchain by downloading specific binary versions of the Motoko compiler (moc), linters (lintoko), and testing tools (pocket-ic) via commands like mops toolchain use.
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute various mops CLI commands to perform project tasks such as installation, building, testing, and linting. These are standard operations for a software development toolchain.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and act upon Motoko project configuration files (mops.toml, mops.lock) and source code (.mo files).
  • Ingestion points: Reads project configuration from mops.toml and dependency lockfiles.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Execution of mops CLI, file system writes (build artifacts, configuration updates), and network access (package downloads).
  • Sanitization: Relies on the underlying mops CLI tool's internal validation of configuration and package integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:44 AM
Security Audit — agent-trust-hub — mops-cli