google-workspace-ops
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious prompt injection patterns, such as instructions to override safety filters or disregard previous rules, were detected in the skill instructions.
- [SAFE]: The skill does not contain any executable code, shell commands, or external script downloads. It relies entirely on the agent's pre-existing tool capabilities for Google Workspace.
- [SAFE]: No data exfiltration or credential harvesting patterns were found. The skill describes standard workflows for interacting with Google Workspace APIs which are intended for the user's benefit.
- [SAFE]: There is no evidence of obfuscation techniques like Base64 encoding, zero-width characters, or homoglyph attacks.
- [SAFE]: While the skill processes external data (reading Google Docs/Sheets), which technically creates a surface for indirect prompt injection, this is the primary and intended purpose of the skill. The instructions emphasize precision and structural inspection, which helps mitigate risks associated with processing untrusted content.
Audit Metadata