openclaw-executive-assistant-workflows

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process external and potentially untrusted data, creating an indirect prompt injection surface.
  • Ingestion points: The skill reads files from the incoming/, inbox/, and eml/ directories (SKILL.md).
  • Boundary markers: The provided prompt templates do not explicitly use delimiters or instructions to treat file content as untrusted data or to ignore embedded commands.
  • Capability inventory: The workflows involve reading local files, writing markdown outputs, and executing local shell scripts for file management.
  • Sanitization: There is no evidence of sanitization or escaping of the input data before it is processed by the AI.
  • [COMMAND_EXECUTION]: The skill documents and provides examples for local task automation.
  • Evidence: The skill includes bash script examples (generate-daily-log.sh) and cron configuration snippets for scheduling workflow execution.
  • Scope: These commands are limited to local file operations such as copying files, appending timestamps, and triggering the prompt processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:46 AM
Security Audit — agent-trust-hub — openclaw-executive-assistant-workflows