gws
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data which may contain malicious instructions designed to subvert the agent's behavior.\n
- Ingestion points: The agent is guided to read external content using
gws gmail users messages get(SKILL.md),gws drive files get(api_reference.md), andgws sheets +read(SKILL.md).\n - Boundary markers: There are no instructions or delimiters provided to separate untrusted content from system instructions, nor any warnings to the agent to treat this data as potentially malicious.\n
- Capability inventory: The skill enables high-impact write operations such as sending emails (
gws gmail +send), uploading files (gws drive +upload), and posting to chat spaces (gws chat +send), which could be abused if the agent follows instructions hidden within ingested data.\n - Sanitization: No sanitization or validation logic is defined for the content retrieved from external Google Workspace services before it is processed by the agent.
Audit Metadata