wireless-technique

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of sudo to execute wireless auditing tools such as airmon-ng, airodump-ng, kismet, hcxdumptool, and hostapd. This is a necessary and standard practice for tasks requiring monitor mode, raw packet injection, and low-level hardware control on Linux systems.
  • [EXTERNAL_DOWNLOADS]: Instructions include downloading the eaphammer tool from a third-party GitHub repository (github.com/s0lst1c3/eaphammer) and installing its requirements via pip. This is standard for deploying specialized security tooling not found in default package registries.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes untrusted data from the environment.
  • Ingestion points: Reads wireless traffic (PCAP/pcapng), device survey results (CSV), and user input from captive portal forms.
  • Boundary markers: The instructions lack specific delimiters or warnings for the agent to ignore potentially malicious instructions embedded within captured network data.
  • Capability inventory: The skill has access to administrative shell execution (sudo) and file system write operations.
  • Sanitization: There is no mention of sanitizing or escaping the content of captured packets or portal responses before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:40 PM
Security Audit — agent-trust-hub — wireless-technique