personality-setup
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the AI to generate and execute
npx skills addcommands. This mechanism is used to install supplementary personality-tuned skills based on the outcome of user assessments. - [EXTERNAL_DOWNLOADS]: The skill references and suggests downloading external code packages from the
crystal-project-inc/personality-ainamespace. These downloads are part of the core functionality to provide specialized personality archetypes. - [PROMPT_INJECTION]: The skill processes user input via responses to multiple-choice quiz questions to determine specific installation commands. This is classified as a surface for indirect prompt injection.
- Ingestion points: User-provided quiz answers processed in the Flow 1 and Flow 2 sections of SKILL.md.
- Boundary markers: None identified.
- Capability inventory: Shell command execution for skill installation (SKILL.md).
- Sanitization: User input is mapped to a predefined list of specific skill names (e.g.,
my-personality-d), which restricts the agent from executing arbitrary skill names based on malicious input.
Audit Metadata