skills/mizchi/skills/gleam-practice/Gen Agent Trust Hub

gleam-practice

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides a CI template (assets/github-actions/ci.yml) that includes a commented-out script to install the Rust toolchain from its official distribution site (sh.rustup.rs). It also suggests standard package management via gleam add for project dependencies.
  • [COMMAND_EXECUTION]: The skill encourages using the just task runner and includes a justfile template (assets/justfile) to automate development workflows including formatting, type-checking, building, and running tests.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user project configuration and source code to provide development guidance. It manages associated risks by promoting strict module boundaries and the use of opaque types to limit internal exposure, alongside encapsulating foreign function interface (FFI) calls.
  • Ingestion points: Workspace project files such as gleam.toml and .gleam source files (specified in SKILL.md).
  • Boundary markers: Encourages usage of internal_modules configuration in gleam.toml and pub opaque type in source code to define strict API surfaces (specified in SKILL.md).
  • Capability inventory: Executes project-specific shell commands via gleam and just (assets/justfile), and writes template files to the local file system (SKILL.md).
  • Sanitization: Relies on architectural recommendations (e.g., adapter patterns for FFI) and the language's static typing to prevent the execution of malicious instructions from processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 04:26 AM