office-hours
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and summarize data from various external sources like pull requests, chat logs, and issue trackers. To protect against potential instructions embedded in this data, the skill includes explicit directives to treat all external text as non-authoritative data and strictly forbids executing any commands or following any instructions found within those sources.
- Least Privilege and Explicit Consent: The skill ensures that no automated actions are taken without user oversight. It specifically requires the user to select 'Create it' before any calendar events are generated and includes clear prohibitions against accessing or exfiltrating sensitive files, credentials, or secrets.
Audit Metadata