review-vitest-tests

Warn

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands, specifically npx eslint --max-warnings 0 <file> and several grep operations, on file paths provided via $ARGUMENTS. Since these paths are user-controlled, they could be exploited for command injection if the underlying execution environment does not properly escape shell metacharacters.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes the content of untrusted test and source files.
  • Ingestion points: Test files and source files provided via $ARGUMENTS in SKILL.md.
  • Boundary markers: Absent. The skill does not instruct the agent to treat the file contents strictly as data or to ignore any embedded instructions.
  • Capability inventory: The agent can execute shell commands (eslint, grep) and read local project files.
  • Sanitization: Absent. There is no logic to filter or validate the content of the ingested files before the agent evaluates them against the checklist.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 30, 2026, 01:46 PM
Security Audit — agent-trust-hub — review-vitest-tests