meta-presentation-design
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised entirely of markdown documentation and reference materials providing methodologies for slide design, narrative structure, and presentation delivery. No executable scripts (.py, .js, .sh), binary files, or network-enabled tools are included or invoked.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a clear ingestion surface for external data such as presentation briefs and business evidence. However, it implements robust defensive instructions under the 'Decision, stop, and recovery controls' and 'Decision Rules' sections. These instructions require the agent to halt when context is missing, verify claims against specific sources, and label all assumptions, which significantly reduces the risk of the agent being manipulated by malicious content within the analyzed business documents.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive local file paths (e.g., .ssh, .aws) were found. The skill operates purely on business logic and textual analysis.
- [COMMAND_EXECUTION]: There is no evidence of shell command execution, subprocess spawning, or the use of dynamic context injection patterns like
!command. The workflow is restricted to read-only analysis and the generation of documentation artifacts.
Audit Metadata