docx

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to read and unpack arbitrary .docx files (see "Text extraction" using pandoc, "Raw XML access" / Unpacking a file, and the "Redlining workflow"), meaning it ingests user-provided/untrusted document content that could carry indirect prompt injections.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The prompt explicitly instructs installing system packages (e.g., "sudo apt-get install pandoc", "sudo apt-get install libreoffice", global npm installs) and other system-level dependency changes that require elevated privileges and can modify the machine state, even though it doesn't instruct creating users or bypassing security mechanisms.