agentic-research-agent-fastapi

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes explicit API-key-like placeholders (e.g., sk-..., tvly-...) and shows examples of embedding keys directly in .env files and command-line -e flags, which encourages or requires placing secret values verbatim in commands/files (an exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.85). The runtime workflow uses the Tavily web search tool (public web content) which returns content strings that are then fed into the research/writer/editor agents’ LLM context during report generation (indirect prompt injection risk from outsider-authored web pages).