typescript-code-and-test-standards

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted project files to determine formatting, linting, and testing standards.
  • Ingestion points: The skill reads project configuration files such as package.json, tsconfig.json, eslint.config.js, .prettierrc, and project-specific rule files like CLAUDE.md and AGENTS.md (documented in SKILL.md and references/project-detection.md).
  • Boundary markers: The skill establishes clear precedence, stating that project-defined rules always take priority over the skill's internal standards (documented in SKILL.md under "Precedence when signals disagree").
  • Capability inventory: The skill utilizes tools to read files, search content, and execute shell commands defined in the project's manifest and build files.
  • Sanitization: No specific sanitization or escaping mechanisms are described for the processed configuration data.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands found in the project's own configuration files (package.json, Makefile, justfile) to run formatters, linters, and test suites.
  • [SAFE]: The skill includes security-conscious instructions, such as the requirement for its sub-agents to redact credential values (tokens, passwords, API keys) when reporting findings (documented in agents/comment-and-jsdoc-auditor.md and agents/test-quality-reviewer.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 10:55 PM