telnyx-email-inbound-curl

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from an untrusted external source (inbound emails), creating an attack surface for malicious instructions embedded in email content.
  • Ingestion points: Email bodies and subjects are retrieved using the GET /email_inboxes/{inbox_id}/messages and GET /email_inboxes/{inbox_id}/threads/{thread_id} endpoints.
  • Capability inventory: The skill allows the agent to perform actions based on this data, including POST .../actions/reply, POST .../actions/reply_all, and POST .../actions/forward, which could be exploited to exfiltrate data or perform unauthorized communications if the agent follows instructions found within an email.
  • Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings to help the agent distinguish between its system prompts and the untrusted email content.
  • Sanitization: There is no evidence of sanitization or filtering of the email content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 06:27 PM
Security Audit — agent-trust-hub — telnyx-email-inbound-curl