retellai-policy-guardrails

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a webhook handler in references/policy-code.md that processes external user transcripts to determine call flow (consent and escalation triggers).
  • Ingestion points: references/policy-code.md processes req.body.transcript.
  • Boundary markers: Not applicable for this code-based implementation.
  • Capability inventory: Modifies call state via retell.call.update and influences the final response generated by the agent.
  • Sanitization: Employs regex and string inclusion checks to identify specific user intent for safety and compliance.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:47 AM
Security Audit — agent-trust-hub — retellai-policy-guardrails