lindy-hello-world

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the user to build an agent that ingests and summarizes webhook payloads ({{webhook_received.request.body}}) and then performs actions like posting to Slack or Gmail. This architecture creates a surface for indirect prompt injection, where a malicious payload could contain instructions designed to manipulate the agent's behavior or exfiltrate data.
  • [COMMAND_EXECUTION]: The skill uses a curl command in the testing phase to simulate a webhook event. The command is used legitimately for testing and utilizes placeholders for sensitive credentials.
  • [EXTERNAL_DOWNLOADS]: The implementation guide references the @lindy-ai/sdk Node.js package and the lindy Python package. These are official/standard libraries for the Lindy platform and are required for the skill's functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:47 AM
Security Audit — agent-trust-hub — lindy-hello-world