network-protocol-attacks
Warn
Audited by Snyk on Nov 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow runs Responder against live network traffic and then reads the captured hash files (usernames and hostnames from peer NTLM/LLMNR traffic) as input to hashcat and john, so an on-segment outsider can influence those strings without the agent selecting a specific item, but the agent does not actively fetch outsider content, so this is a weak, borderline case.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (medium risk: 0.60). The playbook instructs the agent to run offensive network attacks, and several steps change host state that normally needs root: enabling IP forwarding via /proc, appending to the system file /etc/ettercap/etter.dns, loading the 8021q kernel module, and creating VLAN interfaces with ifconfig/vconfig.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata