gws-gmail-forward

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the gws command-line utility to perform email operations. This tool is a prerequisite for the skill and is used to communicate with the Gmail API via the gmail +forward subcommand.- [INDIRECT_PROMPT_INJECTION]: The skill processes content from existing Gmail messages, which are external data sources that could potentially contain malicious instructions or prompt injections. This is a characteristic of the email-forwarding use case.
  • Ingestion points: Gmail message content retrieved by the --message-id flag.
  • Boundary markers: The skill instructions do not define specific delimiters for separating the original message content from the agent's instructions.
  • Capability inventory: The skill is restricted to executing the gws binary for email forwarding, listing, and management.
  • Sanitization: No explicit sanitization of the email body is defined in the skill markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:22 PM
Security Audit — agent-trust-hub — gws-gmail-forward