email-ops

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from incoming email threads and mailbox contents, which creates a vulnerability surface for indirect prompt injection attacks where malicious instructions in an email could attempt to hijack the agent's behavior.
  • Ingestion points: The workflow involves reading existing threads and triaging inbox contents to identify commitments or questions (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' markers to separate untrusted email content from the agent's primary system instructions.
  • Capability inventory: The skill allows the agent to archive messages, draft replies, and execute live sends, providing significant interaction capabilities with the user's mail surface.
  • Sanitization: No explicit instructions are provided for the agent to sanitize, escape, or validate content ingested from external emails before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:41 PM
Security Audit — agent-trust-hub — email-ops