rrrrrredy/skill-security-guard

README excerpt

skill-security-guard Static security scanner for agent skill packages. skill-security-guard performs a deterministic 7-dimension scan, assigns an A-F risk rating, reports confidence levels, and gives remediation guidance. The CLI uses only the Python standard library, so it runs on Windows, macOS, and Linux without project dependencies. It can be used as an OpenClaw skill, as a DeepSeek Harness community Bundle, or as a standalone scanner for local skill packages. What It Scans - Prompt-injection and instruction-override patterns - Sensitive file reads and data exfiltration patterns - Compliance red lines such as tunneling, restricted-system access, highly sensitive data handling, and sensitive config backup/upload - Malicious script patterns in scripts/ - Dependency installation from non-default or suspicious sources - Over-broad or unclear description trigger scopes - Frontmatter compliance ( name and description ) Quick Start Shell wrapper: JSON output: Ignore a reviewed rule for one run: Example Output Safe skill: High-risk skill: Input Support - SKILL.md or any local text/code file - Skill directory containing one or more SKILL.md files - .zip packages, extracted with path tra…

Category