gws-apps-script
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to interact with and execute Google Apps Script code, creating a surface for indirect prompt injection.
- Ingestion points: The agent can read project content and metadata via
projects.get,projects.getContent, andprojects.getMetricsinSKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined in this file to prevent the agent from following instructions embedded within the Apps Script code it reads.
- Capability inventory: The skill allows for writing code (
projects.updateContent), executing code (scripts.run), and managing deployments, which are significant capabilities if the agent is influenced by malicious instructions. - Sanitization: The skill description does not specify any sanitization or validation of the content being read or written.
Audit Metadata