Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed client for sending user-provided video links to LinkDigest for transcription, with no evidence of hidden local access, persistence, or destructive behavior.
Install only if you are comfortable sending video links or share text to linkdigest.dev, using a paid API key, and having text results cached by link on that service. Avoid submitting private or sensitive video links, keep LINKDIGEST_API_KEY out of chat and code, and prefer the included Python script or a pinned MCP bridge version over running an unpinned npx command.
The skill advertises shell, network, and environment-variable usage but does not declare an explicit tool scope such as allowed-tools or permissions. That creates an authorization ambiguity: a host may expose broader capabilities than intended, increasing the risk that future script changes or prompt-injection-influenced execution can access unnecessary tools or secrets.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -sS -X POST https://linkdigest.dev/api/v1/digest \
-H "Authorization: Bearer $LINKDIGEST_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url": "https://v.douyin.com/<短链>/", "format": "json"}'
The skill instructs users to run npx mcp-remote without pinning a specific version or integrity hash. This is a supply-chain risk: a malicious or compromised newly published version could execute arbitrary code on the user's machine at install/run time.
The user-facing natural language in the module docstring, usage text, errors, and argument descriptions is entirely Chinese, and the script does not indicate any opt-in or alternative locale for users who may expect another language. The policy explicitly allows locale constraints only when choice or clear justification is provided, which is not present here.
No suspicious patterns detected.