intercom-sdk-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the use of the official intercom-client package from the NPM registry. This is a well-known and standard dependency for the described functionality.
  • [DATA_EXFILTRATION]: The integration patterns facilitate communication with the official Intercom API. The skill explicitly advises against hardcoding access tokens, instead utilizing environment variables, which is a recommended security practice.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates for processing data retrieved from external Intercom API endpoints.
  • Ingestion points: API responses involving contacts and articles in SKILL.md and references/examples.md.
  • Boundary markers: Generic code skeletons do not define specific data boundaries or 'ignore instructions' wrappers.
  • Capability inventory: The skill enables the agent to Read, Write, and Edit project files to implement SDK patterns; the resulting code interacts with the network and logs data.
  • Sanitization: The patterns provide a structural foundation for API interaction without imposing specific data sanitization, which is typical for library implementation guides.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:45 AM
Security Audit — agent-trust-hub — intercom-sdk-patterns