manage-venue-pages
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 agent to install the official
ticketfairycommand-line interface from the NPM registry (npm install -g ticketfairy). This is a standard installation procedure for the vendor's official tools. - [COMMAND_EXECUTION]: The instructions guide the agent to execute various CLI commands (e.g.,
ticketfairy login,ticketfairy auth status,ticketfairy brand use) to manage venue and brand data. It recommends safety-oriented flags such as--non-interactiveand--read-onlyfor the MCP server to limit the scope of operations. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted user input that is subsequently used in CLI commands and MCP tool calls.
- Ingestion points: User-provided inputs such as venue names, email addresses, brand IDs, and page content (headings, answers) described in
SKILL.md. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands when processing these inputs for tool calls.
- Capability inventory: The skill has capabilities to execute shell commands via the CLI and perform network operations through the MCP server (
get_guide,search_guides). - Sanitization: No explicit sanitization, escaping, or validation of user-supplied strings is mentioned before they are passed to the CLI or MCP tools.
Audit Metadata