recipe-save-email-attachments

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates legitimate data movement between Google Workspace services using the 'gws' utility. No malicious behaviors such as credential theft or unauthorized exfiltration were found.\n- [NO_CODE]: No executable scripts or binaries are bundled with the skill. The functionality relies on external binaries ('gws') and pre-existing skills ('gws-gmail', 'gws-drive').\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data (email content and attachments) and having write capabilities (Google Drive upload). This is inherent to its primary purpose.\n
  • Ingestion points: gws gmail commands for listing and getting messages/attachments (SKILL.md)\n
  • Boundary markers: Not present\n
  • Capability inventory: gws drive +upload (SKILL.md)\n
  • Sanitization: None detected in the instructional steps
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:57 PM