network-tools

Warn

Audited by Snyk on Nov 21, 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 skill is a reference of Linux network commands, and the only outsider-influenced text it would expose the agent to is arbitrary web responses from curl/wget against user-supplied hosts and packet payloads from tcpdump -A, which the agent must actively choose to run.

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

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill exposes state-changing local operations (adding/removing IP addresses and routes, bringing interfaces up or down, and force-killing or port-killing processes), which passes the operational-change gate, but no explicit text establishes irreversible loss of operational state, so it fails the irreversible-loss gate.

Issues (2)

W011
MEDIUM

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

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 11:43 AM
Issues
2