Skills
skills/wadewarren/gws-claude-plugin/recipe-label-and-archive-emails/Gen Agent Trust Hub

recipe-label-and-archive-emails

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gws command-line utility to list messages and modify their labels (adding labels or removing from the INBOX). This is a standard use of the tool for automation.
  • [PROMPT_INJECTION]: The skill interacts with untrusted external data, creating a surface for indirect prompt injection. 1. Ingestion points: Results from gws gmail users messages list in SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: Modification of email labels and archiving threads. 4. Sanitization: No explicit validation or escaping is applied to the data retrieved from Gmail before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:56 PM