implementing-real-user-monitoring

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to interact with and process external web application frontend code.
  • Ingestion points: Accesses frontend code within the ${CLAUDE_SKILL_DIR}/ directory.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions found within the processed code.
  • Capability inventory: The skill utilizes tools for reading, writing, and editing files, along with bash command execution.
  • Sanitization: No sanitization or validation mechanisms are described for handling the content of the external code files.
  • [COMMAND_EXECUTION]: The skill configuration allows for the execution of bash commands via npm:* and rum:* patterns. This is a powerful capability that, while intended for legitimate setup tasks, could be exploited if the agent's logic is subverted by untrusted input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 11:18 AM