meeting-agenda-creation
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to improve productivity by automating meeting agenda creation. It uses standard file search patterns to resolve templates and gather context from the local repository (e.g.,
contacts.md, previous agendas, and project documentation). This data remains within the agent's context for the generation task and is not exfiltrated to any external domains. - [PROMPT_INJECTION]: The skill includes a 'General Doc Constraints' section that enforces strict markdown formatting and character usage (e.g., QWERTY only, specific bullet conventions, and mandatory underscores for italics). These instructions are identified as a stylistic preference for the author's development environment ('KemingHe/common-devx') rather than an attempt to bypass safety filters or override agent autonomy.
- [PROMPT_INJECTION]: The skill processes untrusted content from the repository, such as previous agendas and project documentation, which constitutes a potential surface for indirect prompt injection. However, since the skill's capabilities are limited to generating markdown text for user review and do not involve execution of code or network requests, the associated risk is negligible.
Audit Metadata