inno-idea-eval

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

• Third-party content exposure detected (low risk: 0.10). The skill executes search_ai_papers.py with queries extracted from the idea and ingests search results from external academic APIs (arXiv, Semantic Scholar, OpenAlex) into the novelty verification workflow.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external search script path (~/.claude/skills/searching-ai-papers/scripts/search_ai_papers.py) for runtime execution without bundling or instantiating it, constituting an unverifiable runtime external dependency.