skillguard
Related Servers
Alternatives to skillguard
No user-submitted related servers found.
Related Servers
AlicenseNot gradedqualityDmaintenanceSecurity scanning for AI agent skills exposed as MCP tools, enabling skill analysis from ClawHub, GitHub, skills.sh, or raw URLs.8 npmMIT- FlicenseNot gradedqualityDmaintenanceStatic security scanner for AI agent skill packages that detects malicious SKILL.md files and bundled scripts before they run.15-
- AlicenseNot gradedqualityCmaintenanceProvides a security scanner for AI agent skills and MCP servers, detecting threats like prompt injection, identity hijacking, and memory poisoning.15 npm2MIT
- AlicenseNot gradedqualityDmaintenanceSecurity scanner for AI agent skills, providing tools to scan skill files for threats such as credential theft and prompt injection.MIT

AgentAuditofficial
AlicenseAqualityDmaintenanceEnables AI agents to scan MCP servers and AI packages for vulnerabilities, prompt injection, and supply chain attacks.7118 npmAGPL 3.0- AlicenseAqualityBmaintenanceUnified MCP server that gives AI agents security tools to audit MCP configs, redact secrets/PII, vet skills, check dependencies, and scan networks.6Apache 2.0
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusing it with another tool. Its purpose is clearly described and distinct within the server's scope.
The single tool name 'scan_skill' follows a clear verb_noun pattern, and with only one tool there are no inconsistencies to evaluate.
The server has only one tool, which feels thin for a security scanning domain. While it is comprehensive for single-skill scans, the description references a separate scan_skill_set path that is not exposed, leaving the tool set on the borderline of being too sparse.
The tool thoroughly covers many attack patterns (SG02-SG08, SG10) for a single skill directory, but explicitly lacks SG09 (cross-skill chaining) which requires a separate tool path. This is a notable gap in the security review lifecycle, as multi-skill scenarios cannot be fully assessed.