zendesk
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
npx @useclawlink/clito execute shell commands for authentication and Zendesk API interactions. - [EXTERNAL_DOWNLOADS]: Fetches the
@useclawlink/clipackage from the official npm registry at runtime vianpx. This package is a vendor resource provided by the skill author. - [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process external data from Zendesk tickets, organizations, and user records, which could contain malicious instructions.
- Ingestion points: Data retrieved via
npx @useclawlink/cli run zendesk(SKILL.md). - Boundary markers: The instructions recommend confirming with the user before write operations but do not specify technical delimiters to isolate external data from the system prompt.
- Capability inventory: Shell command execution via the
@useclawlink/clitool. - Sanitization: No explicit filtering or sanitization of retrieved ticket content is mentioned.
Audit Metadata