twilio-customer-memory

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly retrieves customer-written observations and conversation summaries from the public Memory API (memory.twilio.com — e.g., Profiles/{profile_id}/Recall) and injects those untrusted, user-generated contents directly into the LLM system prompt (SKILL.md recall examples), so third-party content can materially influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill issues runtime calls to memory.twilio.com (e.g., POST https://memory.twilio.com/v1/Services/{memory_store_sid}/Profiles/{profile_id}/Recall) and injects the returned observations/summaries directly into the LLM system prompt, so external content from that URL can control agent prompts.