SkillSpector · autoresearch-agent
independent scanner by NVIDIA · skill by DylanCkawalec · how it works ↗
subprocess module calls execute external commands. Without careful input validation, this enables command injection.; Without declared permissions the skill's intent is opaque and cannot be validated.; Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial…; +3 more
scanned 2026-08-23
Findings (20)
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/benchmark_size.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/benchmark_size.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/benchmark_size.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/benchmark_speed.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/benchmark_speed.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/build_speed.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/build_speed.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/llm_judge_content.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/llm_judge_copy.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/llm_judge_prompt.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/llm_judge_prompt.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/memory_usage.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/memory_usage.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
evaluators/test_pass_rate.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/run_experiment.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/run_experiment.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/setup_experiment.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/setup_experiment.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/setup_experiment.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/setup_experiment.py
What the verdicts mean
SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.
Overall severity LOW (risk score in the safe range)
Overall severity MEDIUM
Overall severity HIGH
Overall severity CRITICAL
Scan could not complete