guided-config

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.95). The prompt requires producing README entries with exact commands, config file snippets, and an "Environment Variables" section ("Any secrets or config values needed"), which would force the assistant to include user-supplied secret values verbatim in outputs if provided.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly invites and reviews existing documentation/guide URLs ("Are there existing docs/guides they're following? (URLs welcome)" and "review it and continue building from where it left off"), so the agent is expected to ingest arbitrary user-provided or public web content which could be untrusted.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The prompt explicitly instructs producing and documenting exact commands (including sudo), editing system files under /etc, and running/verifying services (systemctl), which encourages modifying system-level state and using elevated privileges.