Lead Processor

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructions direct the agent to access config/accounts.json, a configuration file likely containing sensitive authentication credentials for email accounts. Accessing such configuration files is a sensitive operation.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted data from external sources (emails).\n
  • Ingestion points: Incoming emails fetched from IMAP mailboxes as described in the triage section of SKILL.md.\n
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from being influenced by malicious instructions embedded within the body of a processed email.\n
  • Capability inventory: The agent can move emails between folders, create drafts in mailboxes, send emails via SMTP (following a keyword confirmation), and update records in an external CRM system (SKILL.md).\n
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the email content before it is summarized, translated, or used to update the CRM database.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 10:25 AM