openclaw-executive-assistant-webinars

Warn

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to clone a repository from an external GitHub account (dandenney/webinars-build-your-own-executive-assistant-with-openclaw.git). This repository is hosted outside the primary vendor's organization and its contents are not verified.\n- [PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted sources, such as unknown files for intake reviews and exported email (.eml) files for triage. This creates a surface for indirect prompt injection attacks where malicious instructions hidden in the files could influence the agent's behavior.\n
  • Ingestion points: Files in code-along/01-data-intake-review/incoming/ and .eml files in code-along/03-offline-communications-triage/eml/.\n
  • Boundary markers: Absent. The provided prompt templates do not utilize XML tags, delimiters, or specific instructions to the model to ignore embedded commands within the processed files.\n
  • Capability inventory: The skill documentation describes interactions with the openclaw CLI tool and mentions the use of shell scripts for automation.\n
  • Sanitization: The skill does not provide methods for sanitizing or validating the content of the external files before they are processed by the LLM.\n- [COMMAND_EXECUTION]: The skill includes instructions for creating shell scripts and configuring cron jobs to automate report generation. While intended for user-driven automation, these actions involve executing commands based on the skill's structure and prompt outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 14, 2026, 08:47 AM
Security Audit — agent-trust-hub — openclaw-executive-assistant-webinars