ux-copy
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill metadata contains a 'risk: critical' flag and links to its community source on GitHub (bitjaru/styleseed), though no dangerous behavior was identified in the analysis.\n- [NO_CODE]: The skill consists only of a SKILL.md file with instructions and does not bundle any scripts, packages, or executables.\n- [PROMPT_INJECTION]: The skill uses the $0 and $ARGUMENTS placeholders to receive user input, which creates a surface for indirect prompt injection.\n
- Ingestion points: Input provided through 'Context: $0' and 'Description: $ARGUMENTS'.\n
- Boundary markers: No delimiters or protective instructions are used to isolate user input from the skill instructions.\n
- Capability inventory: The skill's capabilities are limited to text generation; it lacks any tools for file manipulation, network communication, or system command execution.\n
- Sanitization: No sanitization or filtering is performed on the incoming user data.
Audit Metadata