mcp-tool-schema-generator
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates code and documentation by processing untrusted user input from parameter definitions. This structure allows for potential indirect prompt injection attacks where malicious input in parameter fields could manipulate the generated output or the agent's logic.
- Ingestion points: The skill takes toolName, description, and a parameters array as inputs in SKILL.md.
- Boundary markers: No specific delimiters or instructions are used to isolate untrusted input content during the generation process.
- Capability inventory: The skill is configured with tools for file system interaction including Read, Write, Edit, Bash, Glob, and Grep.
- Sanitization: The skill lacks explicit sanitization or validation of the input strings before they are interpolated into the code generation templates.
Audit Metadata