MCP server que expone los Developer Docs (MD de roadmaps) a TUIs agentic (OpenCode, Codex, Claude Code)
Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.
This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/cli/login.jsView on unpkgSource collects local host identity data and sends it to an external endpoint.
dist/cli/login.jsView on unpkg · L19The login command automatically runs setup after obtaining GitHub credentials, without a separate setup confirmation.
dist/cli/login.jsView on unpkg · L90The user-invoked runtime accepts Harness messages and forwards an inject_skill request to its skill writer.
dist/cli/runtime.jsView on unpkg · L72The skill writer uses unvalidated server-supplied session and skill names to write server-supplied content beneath OpenCode's global skills directory.
dist/skills/injector.jsView on unpkg · L20This report applies to @z2h-academy/tutor@0.5.14.
See version security history for other recorded verdicts.
Evidence last updated: .
Source collects local host identity data and sends it to an external endpoint.
dist/cli/login.jsView on unpkg · L19This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/cli/login.jsView on unpkgThe login command automatically runs setup after obtaining GitHub credentials, without a separate setup confirmation.
dist/cli/login.jsView on unpkg · L90The user-invoked runtime accepts Harness messages and forwards an inject_skill request to its skill writer.
dist/cli/runtime.jsView on unpkg · L72The skill writer uses unvalidated server-supplied session and skill names to write server-supplied content beneath OpenCode's global skills directory.
dist/skills/injector.jsView on unpkg · L20