yy-enable-lint

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install standard development dependencies (such as ESLint, Prettier, Ruff, and Markdownlint) using package managers like npm and pip from official registries. These are well-known technology services used for project quality assurance.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files to determine the appropriate configuration, creating a surface for potential indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: The agent reads project-controlled files including package.json, pyproject.toml, .editorconfig, and directory structures to determine the project type (Step 1).
  • Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers for the content read from these files.
  • Capability inventory: The skill can modify package.json scripts, create new configuration files (e.g., .editorconfig, .markdownlint-cli2.jsonc), write minimal test files, and execute dependency installation commands.
  • Sanitization: There is no explicit requirement to sanitize or validate the content of the ingested configuration files before using them to generate new scripts or configs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 08:08 AM
Security Audit — agent-trust-hub — yy-enable-lint