linter-setup

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from project files (e.g., plan.md, architecture reports) to determine the tech stack, which could potentially be used to influence tool selection or configuration. This is mitigated by mandatory research protocols and user approval gates. \n
  • Ingestion points: plan.md, architecture --mode=design report, and existing CI configuration files. \n
  • Boundary markers: Includes an 'ask user question' step for all tool selections and uses generic search templates rather than hardcoded names. \n
  • Capability inventory: File system writes, package manager execution, and git command execution. \n
  • Sanitization: Requires manual user confirmation for tool choices and strictness overrides.\n- [COMMAND_EXECUTION]: The skill executes shell commands to perform environment detection, install project dependencies through package managers, and verify the integrity of the git hooks.\n- [DYNAMIC_EXECUTION]: The skill generates pre-commit hook scripts and CI job definitions at runtime, which are then executed within an isolated fixture repository to ensure they function correctly.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:12 AM