Basecamp CLI

• Analyzed: May 12, 2026, 3:21 AM
• Findings: 1
• Version: 2.0.0
• Hash: 7f9bdff8267de0a5a2ae12dc41fbec171bf4a1f269f813478f45d5a66c8c2321
• Source: palm
• External report: View on VirusTotal

Findings (1)

The OpenClaw AgentSkills skill bundle is classified as suspicious due to its broad access to Basecamp API functions, particularly the `basecamp_create_webhook` tool exposed via the MCP server (src/mcp/tools/index.ts). While the `payloadUrl` for webhooks is validated to use HTTPS, a compromised AI agent could be prompted to create webhooks pointing to an attacker-controlled endpoint, potentially leading to data exfiltration of Basecamp event data. Additionally, the `scripts/validate.ts` uses `execSync` for command execution, which is a risky capability, though in this context it's used for internal CLI validation. The skill does implement good security practices for token storage by encrypting access and refresh tokens (src/lib/config.ts) and requiring the client secret as an environment variable.