meeting-cost-calculator
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection]: The skill ingests untrusted content from calendar event subjects and attendee lists, which represents a potential attack surface.
- Ingestion points: Untrusted calendar data is retrieved via the
workiq-asktool in Step 2. - Boundary markers: The instructions do not define specific delimiters to isolate potentially malicious meeting subjects from the agent's core instructions.
- Capability inventory: The skill's capabilities are primarily restricted to data aggregation and display; it lacks high-risk tools for file modification, network exfiltration, or arbitrary code execution.
- Sanitization: No explicit sanitization or input validation is specified for the meeting data before it is interpolated into the analysis logic.
Audit Metadata