ticketmaster
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Rule 13 in
SKILL.mdinstructs the agent to "drop it silently" and "do not display it or surface the error text" when a response carries an error. This is a concealment pattern that hides system behavior and failure states from the user. - [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes raw data from external Ticketmaster Discovery API endpoints (such as event names, descriptions, and listing details) and interpolates them into the agent's context.
- Ingestion points: The
search-events,event-details, andtop-pickssubcommands inSKILL.mdingest raw Ticketmaster API payloads. - Boundary markers: There are no instructions for using delimiters or boundary markers when processing external data.
- Capability inventory: The skill executes the
ticketmasterCLI tool and has instructions for reading other skill configuration files on the local filesystem (e.g.,/opt/hatch/skills/booking/SKILL.md). - Sanitization: The instructions lack guidance for sanitizing or filtering potentially malicious strings within the API responses before they are presented to the agent.
Audit Metadata