qa-test-expert

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. Ingestion points: PRD documents and architectural designs (SKILL.md). Boundary markers: Absent. Capability inventory: Executes pytest, locust, ruff, and mypy (SKILL.md). Sanitization: Absent. This surface could allow maliciously crafted external documents to influence agent behavior during test generation or execution.
  • [COMMAND_EXECUTION]: The skill utilizes command-line tools for testing and linting, including pytest, locust, ruff, and mypy. These executions are aligned with the skill's stated purpose of quality assurance and system stability validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 09:06 AM