skill-security-scan

NVIDIA SkillSpector examines Git repositories, URLs, archives, directories, or individual files before an agent skill is installed. It checks dozens of patterns spanning prompt injection, exfiltration, privilege escalation, dangerous code, dependency vulnerabilities, MCP least privilege, and tool poisoning, then produces terminal, JSON, Markdown, or SARIF reports with risk scores. Scanned skills are never executed. Optional LLM analysis sends file contents to the configured provider, while static-only mode keeps that content local.

Snyk Agent Scan finds MCP configurations and Agent Skills used by tools such as Claude, Cursor, Windsurf, and Gemini CLI, then checks for prompt injection, tool poisoning, tool shadowing, malicious payloads, unsafe credential handling, and hardcoded secrets. It runs directly through uvx. Scanning a stdio MCP server executes its configured command, so review the command and approve it only through the consent prompt.

Semia analyzes an Agent Skill before the user decides to trust or run it. The scanner reads the skill as data and never executes its embedded commands, then identifies possible actions, effects, network access, secret reads, and tool invocations with evidence tied to source lines. It can be used through a Python CLI or installed as a plugin for Codex, Claude Code, or OpenClaw. A configured LLM provider is required for the full prepare, synthesize, detect, and report workflow.

AgentDiff captures AI-assisted edits across Claude Code, Cursor, Copilot, Codex, Windsurf, OpenCode, and Gemini, signs line-level attribution with Ed25519, and stores the evidence in Git. Its blame, diff, context, and report commands show who changed what. Pushed traces can expose short prompt excerpts to repository readers, so sensitive teams may need to disable prompt capture.