recipe-forward-labeled-emails

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a workflow that ingests untrusted data from Gmail messages and processes it directly into a new email body, creating a surface for indirect prompt injection.
  • Ingestion points: Gmail message bodies are retrieved dynamically in step 2 using the gws gmail users messages get command in SKILL.md.
  • Boundary markers: Missing. The original message body is directly interpolated into the new email body template without text delimiters or instructions to ignore embedded commands.
  • Capability inventory: Contains communication capabilities through the gws gmail +send command used in step 3.
  • Sanitization: Missing. There is no automated escaping or validation mechanism specified for the content prior to forwarding.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:47 AM
Security Audit — agent-trust-hub — recipe-forward-labeled-emails