data-scraper-agent

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

• Third-party content exposure detected (medium risk: 0.30). In the runtime path scraper/main.py → SOURCES → fetch_fn() → items → ai/pipeline.py::_build_prompt() → ai/client.py::generate(prompt), the agent passes scraped page/API/RSS text (outsider-authored content from the selected public data sources) into Gemini enrichment without constraining or sanitizing it to trusted content.

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

• Potentially malicious external URL detected (high risk: 0.70). The GitHub Actions workflow includes runtime "uses" of external actions (actions/checkout@v4 and actions/setup-python@v5) which the runner fetches and executes as remote code during job execution, creating a dependency on externally-run code (actions/checkout@v4, actions/setup-python@v5).