The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs users to clone a repository from GitHub (https://github.com/dandenney/webinars-build-your-own-executive-assistant-with-openclaw.git) to obtain workshop materials and starter code.
[COMMAND_EXECUTION]: Provides guidance on using chmod +x to make scripts executable and crontab to schedule automated generation of daily logs and weekly summaries. These are documented as standard practices for the skill's automation features.
[PROMPT_INJECTION]: The skill processes untrusted data from external files (e.g., exported emails and unknown incoming files), which presents a potential surface for indirect prompt injection attacks where data content could attempt to influence the AI assistant's instructions.
Ingestion points: Processes files placed in the 01-data-intake-review/incoming/ and .eml files in the 03-offline-communications-triage/eml/ directories.
Boundary markers: No specific boundary markers or 'ignore' instructions are provided in the high-level description to separate data from system prompts.
Capability inventory: The skill is designed to generate markdown reports and triage summaries. It does not perform automated high-privilege operations or network requests based on this data.
Sanitization: There is no evidence of sanitization or filtering of the content within the processed files before they are presented to the AI assistant.

openclaw-executive-assistant-webinar