linter-setup

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository, specifically plan.md and architecture reports, to determine the project's tech stack. This surface could be exploited if those files contain malicious instructions disguised as project documentation.
  • Ingestion points: Reads plan.md, architecture reports, and repository configuration files.
  • Boundary markers: None explicitly used for processing ingested plan or architecture data.
  • Capability inventory: Can execute shell commands (installations, git operations), write configuration files, and perform network searches.
  • Sanitization: No specific sanitization or escaping of project file content is mentioned before it is used to drive tool selection.
  • [COMMAND_EXECUTION]: The skill generates and executes shell commands for tool installation (e.g., npm install, pip install) and project configuration. It also executes commands to configure git hooks and update CI/CD pipelines.
  • [EXTERNAL_DOWNLOADS]: To identify the most relevant tools, the skill uses external web searches. It then facilitates the installation of third-party software packages from standard registries based on the search results and user selection.
  • [DYNAMIC_EXECUTION]: During the verification phase, the skill dynamically creates a temporary fixture repository. It generates test content, stages it, and attempts git commits to verify that the newly configured pre-commit hooks correctly identify and block intentional linting violations.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 06:42 PM