nsis-installer-generator
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface area for indirect prompt injection by accepting untrusted input strings that are subsequently used in file generation or command execution. \n
- Ingestion points: User-provided parameters
appName,version,projectPath, andcomponentsdefined in the input schema withinSKILL.md.\n - Boundary markers: Absent; there are no instructions or system prompts directing the agent to treat these inputs as untrusted data or to use delimiters to separate instructions from data.\n
- Capability inventory: The skill allows access to powerful tools including
Write,Edit, andBash, which can be leveraged to execute shell commands or write to the file system (as defined in theallowed-toolsfrontmatter).\n - Sanitization: There is no evidence of input validation or sanitization logic to prevent malicious payload injection into the generated scripts or shell commands.\n- [NO_CODE]: This skill does not include any standalone executable scripts or binaries (e.g., .py, .js, or .sh files). It functions solely through the AI agent's interpretation of the provided markdown instructions and the generation of text-based templates.
Audit Metadata