Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/retellai-deploy-integration/Gen Agent Trust Hub

retellai-deploy-integration

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill integrates with Retell AI to process voice call data, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: references/deployment-configs.md contains a webhook handler that ingests data from external POST requests through req.body.\n
  • Boundary markers: No explicit delimiters or warnings are present in the example code to instruct the agent to ignore embedded instructions within call transcripts or data.\n
  • Capability inventory: The skill is configured with Write, Edit, and Bash tool permissions in SKILL.md, providing a significant capability surface if call data contains malicious instructions.\n
  • Sanitization: The provided examples do not demonstrate sanitization, filtering, or validation of the ingested event.call data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:48 AM
Security Audit — agent-trust-hub — retellai-deploy-integration