ln-782-test-runner

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines procedures for executing various test frameworks (e.g., Vitest, Jest, pytest, go test, cargo test) and coverage tools (e.g., c8, istanbul, pytest-cov, cargo-tarpaulin). These operations are restricted to the skill's stated purpose of project testing.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves parsing output from external test frameworks. This creates a theoretical attack surface for indirect prompt injection if test logs contain malicious instructions intended to influence the agent's logic.
  • Ingestion points: Test framework execution output (Vitest/Jest JSON reports, pytest output, etc.) in Step 3 and Step 4.
  • Boundary markers: None explicitly defined to delimit test output from agent instructions.
  • Capability inventory: Command execution for test frameworks and reporting results to an orchestrator.
  • Sanitization: Not explicitly mentioned in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 04:08 PM