personal-tool-builder
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes templates for CLI and local-first applications that ingest data via command-line arguments (using
commander) and interactive prompts (usinginquirer). This creates a surface for indirect prompt injection where instructions could be embedded in the processed data. - [COMMAND_EXECUTION]: A dependency checking pattern in
references/detailed-guide.mdusesspawnSyncto verify the presence of external tools likeffmpeg. The implementation follows security best practices by using a fixed argument array rather than a shell string, effectively preventing command injection. - [SAFE]: The skill explicitly teaches defensive coding practices, including binding local servers to
127.0.0.1to prevent network exposure and utilizing environment variables or gitignored config files instead of hardcoding credentials.
Audit Metadata