Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local vegetable-garden calendar planner with disclosed Python commands and no evidence of hidden access, persistence, network use, or data exfiltration.
Before installing, understand that the skill asks your agent to run a local Python script and use your crop list, household size, and frost dates. Verify frost dates with local extension or NOAA data, but no sensitive account, credential, network, or persistent access is evident in the reviewed artifacts.
The skill exposes shell-based commands in its documented interface but does not declare an explicit tool scope such as allowed-tools or permissions. In an agent environment, that omission can let the orchestrator or user invoke broader shell capabilities than the skill strictly needs, increasing the chance of unintended command execution or misuse if the skill is combined with untrusted input.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
def run_cli(args):
return subprocess.run([sys.executable, ENGINE] + args,
capture_output=True, text=True)