External Research
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill is designed to ingest and process content from the live web using tools like read_url_content. Ingestion points: read_url_content tool usage described in resources/quick-reference.md and examples. Boundary markers: Absent; the skill methodology does not specify delimiters for external content. Capability inventory: search_web, read_url_content, and context7 MCP documentation lookup tools. Sanitization: No explicit sanitization or filtering of fetched web content is performed within the provided methodology.
- Data Exposure & Exfiltration (SAFE): A hardcoded SECRET_KEY is present in examples/fastapi-jwt-auth.md. This is identified as a tutorial placeholder for educational purposes rather than an active credential or a leak of user data.
Audit Metadata