skills/timsonner/agent-skills/tcpdump/Gen Agent Trust Hub

tcpdump

Warn

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides various templates for executing the tcpdump utility to capture raw network traffic on the system. This allows the agent to perform low-level network monitoring and packet recording.
  • [PRIVILEGE_ESCALATION]: The use of tcpdump for capturing traffic on network interfaces requires elevated privileges, such as root access or specific Linux capabilities (CAP_NET_RAW). Enabling an agent to run these commands grants it significant administrative-level access to the network stack.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process raw, untrusted network traffic, which serves as an attack surface for indirect prompt injection if the agent interprets the captured data.
  • Ingestion points: Network interface traffic captured via the tcpdump commands in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the captured network packets.
  • Capability inventory: Shell command execution for the tcpdump utility and the ability to write capture files to the local file system using the -w flag in SKILL.md.
  • Sanitization: No sanitization, filtering, or validation of the captured network data is performed before it enters the agent's context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 3, 2026, 02:39 AM
Security Audit — agent-trust-hub — tcpdump