sn1per

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs running web crawls and scans against arbitrary public targets (e.g., "sniper -t https://app.target.com -m web" and descriptions of web crawling using tools like nikto/gobuster/amass), which fetch and parse untrusted third‑party website content that the agent uses to drive follow-up scanning and actions, enabling indirect prompt injection.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill directs the agent to clone and run an install script and to run an automated penetration-testing tool that performs network/attack actions and writes to system paths (e.g., /usr/share/sniper), which likely modifies the host state and may require elevated privileges, so it poses a moderate-to-high risk.