paveman
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a wrapper for the
pavemanCLI tool, which is described as a deterministic, model-free tool that does not use network calls or LLM tokens. - [SAFE]: The skill mandates a security-conscious workflow: it defaults to a dry run (
paveman <file>), requires explicit user confirmation before applying changes (--apply), and informs the user about the rollback capability (--rollback) beforehand. - [SAFE]: Includes a protection validator that prevents the tool from modifying critical sections like code blocks, paths, and headings unless explicitly overridden by the user.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized command execution was found in the skill instructions.
Audit Metadata