foundation-persona

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security concerns were identified during the analysis. The skill operates entirely within the agent's conversational context using provided markdown templates.
  • [PROMPT_INJECTION]: The instructions do not contain any attempts to bypass safety filters, override system instructions, or extract sensitive prompt data.
  • [DATA_EXFILTRATION]: There are no network tools or commands used, and no sensitive file paths are accessed.
  • [COMMAND_EXECUTION]: The skill does not utilize any shell execution, subprocess capabilities, or dynamic code execution.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied context to generate personas, it lacks any dangerous capabilities (like network access or file writing) that could be exploited via indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 06:29 AM