mcore-linting-and-formatting

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run formatting scripts and linting tools within the local environment.
  • Evidence: Executes bash tools/autoformat.sh to apply project-wide formatting rules.
  • Evidence: Runs uv run isort for managing Python import ordering.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the uv package manager to synchronize dependencies, which involves fetching packages from standard registries.
  • Evidence: Uses uv sync --locked --only-group linting to install the required linting toolset.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external source code files which could potentially contain malicious patterns designed to influence the behavior of the linting tools or the agent.
  • Ingestion points: Reads and processes Python source files within the repository (SKILL.md).
  • Boundary markers: Absent; standard developer workflow instructions.
  • Capability inventory: Performs shell command execution and package management (SKILL.md).
  • Sanitization: Not explicitly performed; relies on the security of the underlying linting tools (ruff, black, isort, etc.).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 11:04 AM
Security Audit — agent-trust-hub — mcore-linting-and-formatting