jest-vitest

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform automated system discovery by executing a shell command to list directories in the user's home folder. This behavior is triggered upon activation to identify installed companion skills.
  • Evidence: The 'Companion check' section in SKILL.md requires the agent to run 'ls ~/.claude/skills/ ~/.agent/skills/ ~/.agents/skills/ .claude/skills/ .agent/skills/ .agents/skills/ 2>/dev/null'.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it is designed to ingest and analyze untrusted external project files and code without sufficient security boundaries.
  • Ingestion points: The agent reads and processes user-provided JavaScript/TypeScript test files, package.json, and configuration files such as vitest.config.ts.
  • Boundary markers: Absent. The skill does not define or use specific delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill has the capability to execute shell commands (specifically for environment discovery and running tests) and interact with the file system.
  • Sanitization: No sanitization or validation logic is present for the data ingested from external project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:04 PM
Security Audit — agent-trust-hub — jest-vitest