gws-gmail-read

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a legitimate interface to the gws command-line tool for reading email messages. No suspicious activities, such as credential theft or unauthorized network communication, were detected in the instructions.
  • [PROMPT_INJECTION]: The skill processes external content from Gmail, presenting an inherent surface for indirect prompt injection. 1. Ingestion points: Message body and headers (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions found in this file. 3. Capability inventory: Execution of the gws binary (SKILL.md). 4. Sanitization: The skill documentation mentions automatic HTML-to-text conversion and base64 decoding (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 11:54 PM