Testing

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to run test suites and coverage reports (e.g., pytest, npx jest, npm vitest, mvn test, go test, cargo test). These are expected operations for a testing skill and are clearly documented in the supported languages table.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted user-provided source code to generate and execute tests.
  • Ingestion points: Workflow Step 1 involves reading user-provided source files or directories for analysis.
  • Boundary markers: Absent. The skill does not include instructions to ignore or delimit instructions that might be embedded within the source code (e.g., in comments).
  • Capability inventory: The skill possesses the ability to read and write files and execute arbitrary shell commands through the test runners it invokes.
  • Sanitization: Absent. There is no evidence of validation or sanitization of the source code before it is imported or analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:01 PM
Security Audit — agent-trust-hub — Testing