run-event-social-media
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the official 'ticketfairy' CLI globally via NPM.
- [COMMAND_EXECUTION]: The instructions provide guidance for executing CLI commands such as 'ticketfairy login' and brand management operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Instagram and TikTok to assist in drafting replies and managing events. * Ingestion points: Fan comments and direct messages retrieved via the platform guides or MCP server. * Boundary markers: The skill explicitly requires human approval for all impactful actions, such as posting replies or hiding comments. * Capability inventory: Drafting and posting public replies, sending private messages, and managing presale lists. * Sanitization: The platform relies on manual human review of all generated social media content before it is published.
Audit Metadata