base-station-antenna-monitor
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes patent data from external sources and renders it into an HTML report, creating a surface for indirect prompt injection.
- Ingestion points: Patent metadata including titles, abstracts, and claims are retrieved via the MCP search tool and processed in scripts/run_monitor.py.
- Boundary markers: The script does not use specific delimiters or instructions to ignore embedded content within the patent data.
- Capability inventory: The skill has the capability to write to the local file system to save the report.
- Sanitization: Data is converted to strings and interpolated directly into HTML templates without specific HTML entity escaping, which could allow raw patent content to be rendered as-is.
Audit Metadata