Skills
Navigate
skills/bagelhole/devops-security-agent-skills/datadog/Gen Agent Trust Hub

datadog

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Downloads the official Datadog Agent installation script from its verified Amazon S3 storage bucket.
  • Evidence: bash -c "$(curl -L https://s3.amazonaws.com/dd-agent/scripts/install_script_agent7.sh)" in SKILL.md.
  • [EXTERNAL_DOWNLOADS]: Fetches official Helm charts from Datadog's verified repository.
  • Evidence: https://helm.datadoghq.com in SKILL.md.
  • [COMMAND_EXECUTION]: Instructions include standard system commands for package management and service control to deploy the monitoring agent.
  • Evidence: apt-get install, systemctl start, and systemctl enable in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill configures log ingestion and APM tracing, creating a surface for processing data from applications and system logs.
  • Ingestion points: SKILL.md (Log collection and APM configuration).
  • Boundary markers: Not specified in instructions.
  • Capability inventory: SKILL.md (File writing to /etc/datadog-agent/, system service control, and network connectivity to datadoghq.com).
  • Sanitization: SKILL.md (Uses log processing rules for pattern matching and extraction).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:05 AM