github-issue-from-templates

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses GitHub issue template files at runtime (see "Syncing Configs from GitHub" and "Step 2: Fetch Template from GitHub" in SKILL.md where it runs gh api to download .yml/.md templates into .cache/templates) and then uses that untrusted, user-authored template content to drive field prompts, title/body composition, labels, and gh issue creation, so third-party content can directly influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes the GitHub API at runtime (e.g., via "gh api repos///contents/?ref=") to download issue template/config content which is parsed and directly controls the prompts and fields the agent uses, and when configured to use GitHub storage those remote files are a required dependency.