terminus-maximus

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires copying and preserving the "Original User Request (verbatim)" into planning docs and output, forcing the model to reproduce any user-provided secrets or credentials exactly, which creates an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory Companion Skills (in SKILL.md) require running $skill-oracle which queries external ClawHub and using $context7-docs to pull docs via the Context7 MCP, meaning the agent fetches and interprets third‑party/public content that can change which subroutines and actions it uses.