proof-writer
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a mathematical proof workflow and trigger words. No instructions were found that attempt to bypass AI safety guidelines, override system prompts, or extract internal instructions.
- [DATA_EXFILTRATION]: There are no hardcoded credentials, access to sensitive file paths (e.g., .ssh, .aws), or network-related commands (curl, wget) that could facilitate data exfiltration.
- [REMOTE_CODE_EXECUTION]: The skill does not contain instructions for installing external packages or executing remote scripts. The provided LaTeX snippets are static templates for documentation purposes.
- [COMMAND_EXECUTION]: No shell command execution patterns or dynamic context injection strings were detected in the skill instructions or reference files.
- [SAFE]: The skill acts purely as a structured knowledge base for academic writing, utilizing local markdown files for reference without requesting dangerous permissions or performing suspicious operations.
Audit Metadata