roundtable
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands for environmental setup in Section 9 of SKILL.md. It provides specific instructions for POSIX systems (
date,mkdir) and PowerShell (Get-Date,New-Item) to generate timestamps and ensure output directories exist.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. Ingestion point: User topic input is ingested in Section 2 of SKILL.md. Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the user input. Capability inventory: The skill utilizes shell execution and local file writing capabilities as described in Section 9. Sanitization: The instructions lack explicit sanitization or validation of the user-provided topic keyword before its use in shell-based file management or persona generation.
Audit Metadata