wizard-wx
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines its configuration logic by reading existing project files such as
.env.example,README, and GitHub workflow definitions, which constitutes an indirect prompt injection surface. - Ingestion points: Untrusted data enters the agent's context from local repository files during the initial scoping phase described in
SKILL.md. - Boundary markers: The instructions do not provide specific delimiters or ignore-instructions to prevent the agent from being influenced by malicious content inside these files.
- Capability inventory: Across the provided scripts, the agent is capable of writing files to the local disk and executing shell commands for syntax validation (
bash -n) and permission changes (chmod +x). - Sanitization: There is no evidence of sanitization or filtering of the extracted file content before it is used to generate the bash wizard script.
- [SAFE]: The library in
template.shfollows security best practices, such as using hidden input for secrets (ask_secret) and utilizing the official GitHub CLI (gh) for remote secret management.
Audit Metadata