cml-packet-capture

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface where malicious data within captured packets could influence the agent during the analysis phase.
  • Ingestion points: pcap files downloaded via download_capture in SKILL.md.
  • Boundary markers: No explicit boundaries or warnings for the agent are defined in SKILL.md.
  • Capability inventory: download_capture (file-write and network-read) in SKILL.md.
  • Sanitization: No sanitization of packet content is performed prior to analysis.
  • [EXTERNAL_DOWNLOADS]: The download_capture tool downloads pcap files from the remote CML server to the local system.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:12 AM