manage-brand-and-team
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official
ticketfairyCLI from the well-known NPM registry usingnpm install -g ticketfairy.- [COMMAND_EXECUTION]: The agent uses theticketfairyCLI to manage team memberships and roles through commands such asticketfairy team list,update, andrevoke.- [INDIRECT_PROMPT_INJECTION]: The skill retrieves guide content from external Ticket Fairy documentation which is then processed by the agent. - Ingestion points: External guide content fetched via the
get_guideandsearch_guidestools referenced inSKILL.md. - Boundary markers: Not explicitly defined for the guide data interpolation.
- Capability inventory: Subprocess command execution via the CLI and network operations via MCP.
- Sanitization: Includes a mandatory safety protocol requiring the agent to wait for the user's explicit consent before performing any destructive or state-changing operations ("Confirm before you change anything").
Audit Metadata