Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently runs a local report generator on user-provided CSV/XLSX files and writes report outputs, with no evidence of hidden persistence, exfiltration, or destructive behavior.
Install only if you are comfortable having a local ReportStudio Python module read selected CSV/XLSX files and create XLSX/PDF/PPTX reports, usually under ./artifacts. Review generated reports before sharing them, since they may contain business-sensitive summaries from the input data.
The skill invokes shell execution (python -m reportstudio.cli.main) but does not declare any tool scope or permission boundary. In agent environments, undeclared shell capability weakens policy enforcement and can enable broader-than-expected code execution against local files and the runtime environment.
The trigger text is broad enough that ordinary requests about reports, trends, or PPT/PDF materials could activate the skill without clear boundaries. Over-broad activation can cause the agent to run shell-based file-processing unexpectedly on sensitive local data, increasing the chance of unintended access or artifact creation.
The natural-language instructions and examples are written entirely in Chinese, including the trigger examples and workflow text, with no indication that other languages are supported or that Chinese is required for a region-specific purpose. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
This markdown file contains user-facing natural-language instructions only in Chinese, which can violate language/locale policy when no user opt-in or alternative language path is provided. The file does not state that the skill is region-specific or otherwise limited to Chinese-speaking users.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
cmd += ["--time-range", ns.time_range]
cwd = ns.repo_dir or None
p = subprocess.run(cmd, cwd=cwd, check=True, capture_output=True, text=True)
payload = json.loads(p.stdout)
The skill writes XLSX/PDF/PPTX artifacts to an output directory but does not clearly warn users up front that files will be created on disk. This can lead to unintended persistence of potentially sensitive business data in local directories, backups, or shared workspaces.
No suspicious patterns detected.