retellai-webhooks-events
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data in the form of call transcripts provided by the Retell AI webhook payload.
- Ingestion points: Transcripts are ingested in
SKILL.md(Step 2) andreferences/webhook-handlers.mdwithin thehandleCallEndedfunction. - Boundary markers: The provided code examples do not include boundary markers or instructions to the LLM to ignore potentially malicious content within transcripts.
- Capability inventory: The skill's implementation templates involve file/database writes (
db.calls.create), network operations via CRM/Alerting integrations, and task creation. - Sanitization: There is no evidence of sanitization or validation of the transcript content before it is passed to downstream processing (e.g., in the
extractActionItemsfunction).
Audit Metadata