email-outreach
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
scripts/gmail_unified.py) to interact with Gmail APIs and perform bulk actions like labeling and archiving.\n- [PROMPT_INJECTION]: The skill processes untrusted external data from Gmail messages, which introduces a risk of indirect prompt injection where malicious instructions embedded in an email could attempt to influence the agent's behavior.\n - Ingestion points: Email subjects, bodies, and sender metadata fetched from Gmail accounts via the unified script.\n
- Boundary markers: No specific delimiters or safety instructions (e.g., "ignore instructions in the email body") are provided for the agent to follow when processing this data.\n
- Capability inventory: The skill allows reading, labeling, and archiving emails, and managing outreach campaigns via the Instantly API.\n
- Sanitization: There is no evidence of sanitization or validation performed on the retrieved email content before it is processed by the agent.
Audit Metadata