Weather Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and examples for weather automation. No malicious command execution, data exfiltration patterns, or hardcoded credentials were detected. The skill author and infrastructure references appear consistent with the intended purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection because it processes external data from weather services and calendar events, though this behavior is inherent to its function and no active exploitation is present.
- Ingestion points: External weather data via MCP tools and calendar event metadata (e.g.,
{{event.location}}) used in workflow templates in SKILL.md. - Boundary markers: None present in the workflow examples to separate instructions from dynamic data.
- Capability inventory: No subprocess calls, file system writes, or direct network operations are defined; capabilities are limited to weather tool invocation and notification triggers (Slack, SMS, Home Assistant).
- Sanitization: No explicit sanitization or validation logic is provided in the skill instructions to handle potentially malicious content in the external data strings.
Audit Metadata