mcp-deploy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to collect API keys and tokens from the user and embed them directly into command-line arguments and configuration commands (e.g., using placeholders like YOUR_API_KEY in mcporter config add).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to guide users through deploying MCP servers, including downloading binaries from Gitea releases referenced via a URL, which involves low-risk access to external web pages/downloads.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch and execute an installation script from astral.sh, representing a common/reputable unofficial operational dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill suggests copying a binary to /usr/local/bin/ which requires root/sudo privileges on most standard systems, potentially compromising the machine state.