ip-management

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The prompt includes a "Companion check" that explicitly instructs the agent to run local shell commands and offer installs (ls ~/.claude/skills/... and npx install), which is outside the stated IP-management purpose and asks the agent to access/modify the host environment, so it is a deceptive/out-of-scope instruction.

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows (e.g., "File a trademark application" clearance search that explicitly directs searching the USPTO TESS and "common-law sources (web, app stores, domain registrations)" and the "Audit open-source dependencies" process that runs SCA tools against public package data) require fetching and interpreting public/untrusted web content which can materially change decisions or actions.