The Agent Skills Directory

[SAFE]: The skill uses environment variables (INTERCOM_TOKEN) for API authentication, which is a secure method for managing sensitive credentials.
[COMMAND_EXECUTION]: Provides standard curl commands to perform authenticated HTTP requests for managing conversations, contacts, and help center articles.
[EXTERNAL_DOWNLOADS]: The skill interacts with official, well-known Intercom API endpoints (api.intercom.io, api.eu.intercom.io, api.au.intercom.io) to facilitate legitimate service operations.
[DATA_EXFILTRATION]: Facilitates the transmission of customer data and conversation history to the Intercom platform as intended by the skill's primary purpose.
[PROMPT_INJECTION]: The skill processes data from external Intercom conversations, which presents a surface for indirect prompt injection.
Ingestion points: Intercom API responses containing messages from external customers.
Boundary markers: None present in the provided command templates.
Capability inventory: Network operations via curl and local file writes to /tmp.
Sanitization: No specific validation or escaping of API-returned content is defined in the documentation.

intercom