electronegativity

Skill Scanner checks individual skills, directories, or repositories with static rules, shell-pipeline taint analysis, Python dataflow analysis, and optional LLM or cloud engines. It can produce SARIF or HTML reports and run in CI or pre-commit workflows with custom policies. Results are best effort: finding nothing does not certify a skill as safe, so human review remains necessary.

GlobalProtect-openconnect provides Linux users with CLI and graphical clients built around OpenConnect. It can connect to multiple portals or gateways and supports SSO, non-SSO login, FIDO2 devices such as YubiKey, and client certificates. The CLI is free and open source, while the GUI is a paid application with a seven-day trial after installation.

SkillWard triages Agent Skills in three stages: rule-based static analysis, LLM-assisted intent evaluation, and isolated Docker execution for unresolved cases. The runtime guard records evidence of suspicious network access, sensitive writes, credential risks, and other behavior. It supports single or batch CLI scans, with an optional web interface for reviewing results.

Place the scanner between untrusted content, model output, and tool execution, or wrap a line-delimited stdio MCP server with its proxy. It detects prompt injection, credential disclosure, exfiltration, and destructive actions before forwarding a call, redacts secrets, and returns structured reasons for enforcement. The scanner makes no network calls and ships as a Rust CLI with Node and Python wrappers.