new-venue-openings
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the Hedwig AI MCP server (https://mcp.hedwigai.com/) and associated plugins under the un-seen namespace. These are legitimate vendor resources required for the tool's intended functionality and do not represent a security risk.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external business license registries, which acts as a theoretical ingestion surface for indirect prompt injection. However, the risk is minimal as the skill uses structured processing and specific reporting commands. (1) Ingestion points: Data retrieved via the us-business-license tool in SKILL.md. (2) Boundary markers: None explicitly defined. (3) Capability inventory: Uses bash (for jq and license tools) and create_workbook. (4) Sanitization: Employs jq for structured parsing of external JSON data.
Audit Metadata