list-week-meetings
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted meeting information from the Outlook web interface, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Meeting titles, descriptions, and organizer details are extracted using the
chrome-cdp snapcommand inSKILL.md(Phase 3). - Boundary markers: The skill does not use specific delimiters or instructions to ignore potential commands embedded within the meeting data.
- Capability inventory: The skill uses the
chrome-cdpCLI to control a browser, navigate pages, and read content. - Sanitization: There is no evidence of sanitization or filtering applied to the extracted meeting data before it is presented.
Audit Metadata