intercom-automation
Warn
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to configure an external MCP server endpoint at https://rube.app/mcp. This third-party service is not on the trusted vendor list and should be vetted before use.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through data ingested from Intercom. * Ingestion points: The skill reads external content through tools like INTERCOM_LIST_CONVERSATIONS and INTERCOM_SEARCH_CONTACTS in SKILL.md. * Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions embedded within Intercom messages or metadata. * Capability inventory: The skill possesses write capabilities including INTERCOM_REPLY_TO_CONVERSATION and INTERCOM_ASSIGN_CONVERSATION. * Sanitization: The skill mentions HTML sanitization for rendering but does not specify sanitization or filtering for malicious instructions.
Audit Metadata