webex-user-context
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from external sources (WebEx messages and real-time notifications) to determine context, response styles, and escalation routing, creating a surface for indirect prompt injection.
- Ingestion points: The skill uses the 'Messages -- List' API and 'Webhooks' to read recent messages for context and receive real-time notifications in SKILL.md.
- Boundary markers: None identified. The instructions do not provide delimiters or specific guidelines for the agent to treat message content as untrusted data rather than instructions.
- Capability inventory: The skill performs escalation routing, personalized response generation, and integrates with alert and incident workflow skills (webex-network-alerts, webex-incident-workflow) as described in SKILL.md.
- Sanitization: There is no mention of sanitization, filtering, or escaping of the message content before it is interpolated into the agent's context.
Audit Metadata