wizard
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates a Bash script that performs local file system operations (upserting values to
.envfiles) and uses the GitHub CLI (gh) to set repository secrets and variables. These operations are performed at the user's direction when they execute the generated script. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes local repository files, such as
README.mdand.env.example, to determine necessary configuration stages. This creates an ingestion surface for data that could potentially contain malicious instructions; however, the skill mitigates this by requiring the agent to present the scoped stages to the user for confirmation before any code is generated. - [DYNAMIC_EXECUTION]: The core functionality of the skill involves authoring a new executable script based on the provided
template.sh. This script generation is a transparent process guided by templates and intended for one-off or repeatable setup tasks verified by the user.
Audit Metadata