Skills
skills/jeremylongshore/claude-code-plugins-plus-skills/creating-apm-dashboards/Gen Agent Trust Hub

creating-apm-dashboards

Warn

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts create_datadog_dashboard.py and create_grafana_dashboard.py dynamically generate shell scripts (.sh) from user-provided templates and programmatically grant execution permissions using chmod(0o755).
  • [COMMAND_EXECUTION]: The SKILL.md file grants the agent broad execution privileges through the Bash(cmd:*) tool, allowing arbitrary command execution on the host environment.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted user data to generate executable code.
  • Ingestion points: User-provided strings via the --content and --title arguments in the generation scripts.
  • Boundary markers: None identified; user input is directly interpolated into the shell script templates without delimiters.
  • Capability inventory: The skill possesses the ability to write files (Write), modify existing files (Edit), and execute arbitrary shell commands (Bash(cmd:*)).
  • Sanitization: There is no evidence of validation, escaping, or sanitization of user-provided content before it is written to executable files and assigned execution permissions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 12:28 AM