Skills
Navigate
skills/abcnuts/manus-skills/realistic-ai-persona-builder/Gen Agent Trust Hub

realistic-ai-persona-builder

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Instructions in SKILL.md and references/prompt-optimization.md recommend executing a Python script using shell variable interpolation (e.g., python scripts/validate_prompt_length.py "$PROMPT" 4000). If the content of the prompt variable contains shell metacharacters like backticks or subshell markers, it could lead to arbitrary command execution in the environment where the script is invoked.
  • [SAFE]: The Python utility scripts provided with the skill (scripts/example.py and scripts/validate_prompt_length.py) are benign and do not perform any privileged or dangerous operations.
  • [SAFE]: The persona-building instructions are specific to character development and do not contain patterns typical of direct prompt injection or system prompt extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:23 AM
Security Audit — agent-trust-hub — realistic-ai-persona-builder