gerador-soul
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a template-based generation process that ingests user-supplied agent descriptions and instructions. There is an inherent surface for indirect prompt injection as user input is interpolated into the generated SOUL.md and instructions.txt files without explicit sanitization or boundary markers. However, the skill lacks any capabilities to execute code, access the network, or perform file operations beyond text generation, making the risk negligible.
- [NO_CODE]: The skill is comprised entirely of Markdown files, providing instructions and examples for text generation. It does not include any scripts, binaries, or tool invocations that could be used for malicious purposes.
- [SAFE]: The skill follows best practices for behavioral constitution generation and uses local reference files for its internal logic, presenting no evidence of malicious patterns, obfuscation, or data exfiltration.
Audit Metadata