Security audit
Security checks across malware telemetry and agentic risk
The skill appears to perform Douyin scraping as advertised, but it asks for and stores live Douyin login cookies/session state and has avoidable command-execution handling risks that merit review before installation.
Install only if you are comfortable giving the skill access to a logged-in Douyin session. Prefer placing cookies in the local file yourself instead of pasting them into chat, protect and delete cookie/state files when done, expect local exports and optional video downloads to consume disk space, and review the shell=True agent-browser eval implementation before using it on a shared or sensitive machine.
"""通过临时文件执行 ab eval(避免 shell 转义)"""
js_file = str(TMP_DIR / "_ab_eval_tmp.js")
Path(js_file).write_text(js)
return subprocess.run(
f"agent-browser eval \"$(cat {js_file})\"",
shell=True, capture_output=True, text=True, timeout=timeout,
)js = HARVEST_JS_AGGRESSIVE
js_file = str(TMP_DIR / "_harvest_oneshot.js")
Path(js_file).write_text(js)
r = subprocess.run(
f"agent-browser eval \"$(cat {js_file})\"",
shell=True, capture_output=True, text=True, timeout=120,
)js_file = str(TMP_DIR / "_harvest_step.js")
Path(js_file).write_text(js)
# 初始化(第一次 eval 走初始化分支)
r = subprocess.run(
f"agent-browser eval \"$(cat {js_file})\"",
shell=True, capture_output=True, text=True, timeout=15,
)})()
"""
Path(str(TMP_DIR / "_harvest_flush.js")).write_text(flush_js)
r = subprocess.run(
f"agent-browser eval \"$(cat {TMP_DIR}/_harvest_flush.js)\"",
shell=True, capture_output=True, text=True, timeout=10,
)stalled = 0
total_added = 0
for rnd in range(max_rounds):
r = subprocess.run(
f"agent-browser eval \"$(cat {js_file})\"",
shell=True, capture_output=True, text=True, timeout=20,
)err(f" round {rnd+1} eval 失败: {r.stderr[:100]}")
# 重试 1 次
time.sleep(2)
r = subprocess.run(
f"agent-browser eval \"$(cat {js_file})\"",
shell=True, capture_output=True, text=True, timeout=20,
)}})
.filter(Boolean)
)""")
r = subprocess.run(
f"agent-browser eval \"$(cat {eval_file})\"",
capture_output=True, text=True, timeout=15, shell=True,
)const avatar = !!document.querySelector('[class*="avatar"]:not([class*="placeholder"])');
return JSON.stringify({title, captcha, loginPanel, userInfo, avatar});
})()"""
r = subprocess.run(
f"agent-browser eval \"$(cat <<'EOF'\n{check_js}\nEOF\n)\"",
capture_output=True, text=True, timeout=10, shell=True,
)64/64 vendors flagged this skill as clean.
Detected: suspicious.dynamic_code_execution