ln-782-test-runner

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions specify fetching components from the author's GitHub repository (github.com/levnikolaevich) using WebFetch if local shared directories are missing.
  • [COMMAND_EXECUTION]: Executes shell commands to run test suites for various frameworks including Vitest, Jest, xUnit, pytest, go test, and cargo test based on project discovery.
  • [PROMPT_INJECTION]: Susceptible to indirect prompt injection through the processing of untrusted data from test logs.
  • Ingestion points: Test framework console output and logs parsed during result extraction (SKILL.md).
  • Boundary markers: Absent; no delimiters or instructions are provided to the agent to ignore embedded commands within test output.
  • Capability inventory: Shell command execution via Bash and Monitor tools.
  • Sanitization: Absent; the skill parses external test output directly without validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 08:33 AM