creating-github-issues-from-web-research

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

• Third-party content exposure detected (high risk: 1.00). This skill's SKILL.md explicitly instructs the agent to perform web searches and "extract relevant details" (Web Search / Information Extraction steps) and bundled files (scripts/web_search_parser.py, assets/example_search_results.json, and config_template.json web_search settings) show it ingests public URLs (e.g., forums, GitHub, NVD) so untrusted third-party content is read and used to generate GitHub issues, which could materially influence subsequent actions.