pp-printing-press-oauth2

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's playbook/recall instructions explicitly include a "token" in slots_resolved and require replaying steps with slot substitution, which would force the agent to insert live tokens/credentials verbatim into commands or outputs (an exfiltration risk).

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These point to a personal GitHub repo and a GitHub release that distributes pre-built binaries (.mcpb / CLI) from a non-official/personal source — a common vector for malware distribution — while the remaining URLs are placeholder API endpoints or known/third-party repos and are not flagged.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing and running a remotely fetched CLI (via the npx installer) or downloading a pre-built binary from the GitHub release URL https://github.com/mvanhorn/printing-press-library/releases/tag/printing-press-oauth2-current at runtime, which fetches and executes remote code needed for the skill to operate.