ic-leaderboard

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the user to paste a GitHub Personal Access Token and instructs the agent to include that PAT verbatim in API calls/command bodies or tool arguments (curl -d and MCP "pat" argument), which requires the LLM to handle and potentially emit the secret directly.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). INSTALL.md contains curl commands that fetch https://www.immersivecommons.com/skills/ic-leaderboard/SKILL.md into the agent's skills folder (and instructs pointing the client at https://www.immersivecommons.com/api/mcp for MCP tool discovery), which are runtime fetches of remote instruction/tool definitions that directly control agent behavior.