intercom-webhooks-events

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a webhook endpoint that processes external JSON data from Intercom, creating a potential surface for indirect prompt injection.
  • Ingestion points: references/incoming-webhooks.md defines an Express route /webhooks/intercom that parses raw request bodies provided by the Intercom service.
  • Boundary markers: The implementation includes HMAC-SHA1 signature verification to ensure data origin, but does not provide delimiters or instructions to the agent to ignore potentially malicious content embedded within the webhook payload data.
  • Capability inventory: The skill is configured with Bash(curl:*) capabilities in SKILL.md, and the provided code includes handlers that perform logging and logic based on the untrusted input.
  • Sanitization: No explicit sanitization or schema validation of the notification.data.item object is implemented before the data is processed by the event handlers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:44 AM
Security Audit — agent-trust-hub — intercom-webhooks-events