腾讯文档Markdown
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This appears to be a disclosed Tencent Docs Markdown automation tool, but it stores account cookies and can modify or delete Tencent documents.
This skill looks coherent for Tencent Docs Markdown automation. Before installing, be comfortable granting it access to your Tencent Docs session, protect the .cookies.json file, verify document URLs before update/delete/rename actions, and avoid using it with highly sensitive documents unless you trust the agent session and machine.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Anyone who obtains the cookie file may be able to act on your Tencent Docs account.
The skill stores reusable Tencent Docs session cookies locally, which are account-level credentials.
This file grants full access to your Tencent Docs account. • Do NOT commit it to version control or share it with anyone.
Use a dedicated automation account if possible, keep .cookies.json private, and run the logout command or delete the file when finished.
If used on the wrong URL or with confirmation bypassed, a document could be overwritten, renamed, or moved to trash.
The skill can overwrite, rename, or delete Tencent Docs documents. The artifacts include confirmation gates, but also document explicit bypass options.
更新...这是破坏性操作...程序化调用须显式传入 confirm=True...CLI 也可加 -y/--yes 跳过提示.
Check the document title and URL before approving destructive actions, and avoid -y/--yes unless you are certain.
Sensitive document content could appear in chat logs, terminal output, local files, or downstream tool calls.
Reading or downloading documents intentionally brings their contents into the agent session and may write them to disk.
document content will be exposed to the caller / agent session... The downloaded content is written to the local filesystem and returned to the caller.
Do not use read/download on highly sensitive documents unless you trust the current agent session and local environment.
Installation depends on external package and browser downloads, which carry normal supply-chain risk.
The install script downloads Python dependencies and a Playwright Chromium browser. Dependencies are version-pinned, but the fallback install does not enforce hashes.
"install": "pip install --require-hashes -r requirements.txt 2>/dev/null || pip install -r requirements.txt && playwright install chromium"
Install in a trusted environment, review dependencies, and prefer locked or hash-verified installs where possible.