Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name and description match the SKILL.md: the skill's goal is to send up to 5 local files into the current Kimi conversation. Nothing in the metadata or SKILL.md requests unrelated services, binaries, or credentials.
Instruction Scope
The SKILL.md tells the agent to call kimi_upload_file(paths=[...]) to send arbitrary local files. That is in-scope for a file-transfer skill, but the instructions are terse and grant the agent authority to read and upload any local path the user names (examples include paths like memory/db-ai-agent-strategy.md). There are no explicit constraints, confirmation steps, or warnings about sensitive files, so the agent could easily be used to exfiltrate secrets or internal state without safeguards.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes install risk because nothing is written to disk by the skill bundle itself.
Credentials
No environment variables, credentials, or config paths are requested. However, the skill implicitly depends on a tool (kimi_upload_file) and on the agent having filesystem access and upload capability. The SKILL.md does not document what permissions the kimi_upload_file tool requires or who can access uploaded files.
Persistence & Privilege
always is false and there is no install behavior that would make the skill persistent or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other elevated privileges here.
What to consider before installing
This skill appears to do what it says (upload local files to the Kimi conversation) but the runtime instructions allow the agent to read and upload any local path you specify — including possibly sensitive internal files (agent memory, credentials, logs). Before installing or using it, verify: (1) what the kimi_upload_file tool does and who can access the uploaded files on the server, (2) that the agent will prompt for explicit confirmation before uploading sensitive paths, and (3) you avoid naming or auto-sending files that contain secrets (API keys, ~/.ssh, agent memory or database files). If you need stricter safety, request that the skill author add explicit confirmation steps, a whitelist of allowed directories, or a preview of files to be uploaded.Like a lobster shell, security has layers — review code before you run it.
file-transfervk976f63zg723jbt7cmnsawrrgx8200crkimivk976f63zg723jbt7cmnsawrrgx8200crlatestvk976f63zg723jbt7cmnsawrrgx8200cruploadvk976f63zg723jbt7cmnsawrrgx8200cr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.