gws-alertcenter
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests potentially untrusted data from external security alerts which could contain malicious instructions or deceptive content.
- Ingestion points: Data retrieved from Google Workspace Alert Center via methods such as
alerts.listandalerts.getdefined inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or warnings to separate processed alert content from the agent's system instructions.
- Capability inventory: The skill provides methods for modifying environment state, including
alerts.delete,alerts.batchDelete, andv1beta1.updateSettings. - Sanitization: There are no instructions provided for sanitizing or escaping the content of alerts before the agent processes them.
Audit Metadata