solve-ticketing-problems
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the official Ticket Fairy CLI tool via
npm install -g ticketfairy. This is a vendor-owned package consistent with the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external data from guides and search results.
- Ingestion points: External data enters the agent context via the
search_guidesandget_guidetools from the MCP server athttps://www.ticketfairy.com/docs/mcp. - Boundary markers: The instructions mandate following the guides exactly rather than relying on memory, though no explicit delimiters for the external content are specified in the markdown.
- Capability inventory: The agent can execute commands using the
ticketfairyCLI and perform actions via the MCP server. - Sanitization: The skill includes robust instructions for the agent to keep secrets (tokens, passwords) out of the chat, to use personal access tokens via environment variables (
TICKET_FAIRY_API_KEY), and to obtain explicit user approval before any write or state-changing operations.
Audit Metadata