add-github

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly prompts for a GitHub personal access token and webhook secret and then instructs writing those values into .env via template placeholders (nc:prompt + nc:env-set), which requires the agent to handle and output the secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md configures a GitHub webhook on Issue comments and Pull request review comments, which supplies outsider-authored comment text to the required runtime workflow via PR/issue comment threads.