gws-gmail-reply

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content from email messages during reply generation.
  • Ingestion points: SKILL.md describes capabilities for pulling down and replying to Gmail messages containing user-supplied bodies or HTML formatting.
  • Boundary markers: None specified in standard flags or commands.
  • Capability inventory: The skill utilizes the gws command-line binary to interact with the Gmail API, performing email generation and sending functions.
  • Sanitization: No sanitization mechanisms are detailed for incoming or outgoing body interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:22 PM
Security Audit — agent-trust-hub — gws-gmail-reply