flight-to-calendar
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data that could contain hidden instructions intended to manipulate the agent's behavior.
- Ingestion points: The skill reads data from user-provided flight itineraries, e-tickets, and PNR details (referenced in SKILL.md under the '取資料' section).
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to differentiate between the data being processed and potential instructions embedded within that data.
- Capability inventory: The skill has the capability to write to the user's calendar using the
create_eventandupdate_eventtools from the Google Calendar MCP. - Sanitization: The instructions do not include steps to sanitize, validate, or escape the content extracted from external files before it is processed by the agent.
Audit Metadata