Security audit
Security checks across malware telemetry and agentic risk
The skill mainly matches its advertised Baidu Zhidao posting purpose, but it includes under-disclosed browser evasion, local profile fallback, and optional AI-generated posting paths that should be reviewed before installation.
Install only if you are comfortable with an agent posting publicly to Baidu Zhidao using a saved browser/account session. Review the target URL, account, and answer file before each run, avoid the direct_rpa_run.py --optimize/--auto-approve path unless you intentionally want external AI generation, and be aware that local logs, records, and browser-profile data are used.
script_path = os.path.join(get_skills_root(), skill_slug, "scripts", "main.py")
if not os.path.isfile(script_path):
return None
proc = subprocess.run(
[sys.executable, script_path, *args],
capture_output=True,
text=True,VirusTotal findings are pending for this skill version.
No suspicious patterns detected.