linux-privilege-escalation

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

• Third-party content exposure detected (low risk: 0.10). The skill references GitHub and GTFOBins URLs for community scripts and documentation lookup, which represent low-risk external content retrieval.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches a third-party script from GitHub via curl during runtime enumeration, presenting a weak/unknown provenance operational dependency.

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 prompt instructs the agent on performing Linux privilege escalation attacks, including executing exploits, modifying cron jobs, and bypassing security configurations to gain root access.