recipe-label-and-archive-emails
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for searching and modifying Gmail messages based on external data. This creates an attack surface where instructions embedded in processed emails could potentially influence agent behavior.
- Ingestion points: The agent is instructed to read the output of
gws gmail users messages listto identify specific emails (SKILL.md). - Boundary markers: Absent. The skill does not provide delimiters or instructions for the agent to ignore potential commands found within the email content.
- Capability inventory: The agent has the capability to search, add labels to, and archive (remove from inbox) Gmail messages using the
gwsCLI tool. - Sanitization: Absent. There are no mechanisms described to sanitize or validate the email metadata or content before the agent uses it to perform subsequent actions.
Audit Metadata