superclaude-framework-compat

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs agents to perform web fetches of public, user-generated sources (e.g., "WebFetch: Stack Overflow, GitHub Issues, community solutions" in pm.md's Root Cause Investigation and WebSearch in brainstorm.md), which the agent is required to read and use to drive investigation and remediation decisions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.50). The prompt instructs running a PowerShell script with "‑ExecutionPolicy Bypass" (bypassing a security mechanism), but otherwise only operates on user-home files and does not request sudo, modify system-wide config, or create users.