officecli
Fail
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the user to execute code directly from a remote URL by piping it to a shell (e.g., 'curl -fsSL https://d.officecli.ai/install.sh | bash' and 'irm https://d.officecli.ai/install.ps1 | iex' in SKILL.md). This pattern is inherently dangerous as it bypasses local security inspections and allows the remote server to execute arbitrary commands on the host system.
- [COMMAND_EXECUTION]: The skill uses various shell commands to invoke the 'officecli' tool for document creation and manipulation (SKILL.md).
- [EXTERNAL_DOWNLOADS]: The skill initiates network requests to 'https://d.officecli.ai' to download installation scripts (SKILL.md).
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external Office documents (.docx, .xlsx, .pptx) via commands like 'view', 'get', and 'query' in SKILL.md without boundary markers or sanitization. This content is then used within the agent's context, providing a surface for malicious instructions embedded in documents to influence agent behavior, especially given the skill's file-system manipulation capabilities ('set', 'add', 'move', 'remove' in SKILL.md) and initial network capabilities.
Recommendations
- HIGH: Downloads and executes remote code from: https://d.officecli.ai/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata