The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the user, such as details of renovation work, counterparty identifiers, and pasted WhatsApp chat logs (referenced in Steps 1 and 9 of SKILL.md). The instructions do not define boundary markers or sanitization steps to protect the agent from instructions that might be embedded in this user-supplied data.
Ingestion points: User-provided renovation scopes, contractor details, and chat history exports in SKILL.md and SKILL_HE.md.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are prescribed for the interpolation of user data.
Capability inventory: The skill can execute a local Python script (scripts/payment_schedule.py) and generate detailed legal templates.
Sanitization: There are no instructions for the agent to sanitize or escape content from external data sources.
[COMMAND_EXECUTION]: The skill uses a bundled Python script (scripts/payment_schedule.py) to perform arithmetic validation on payment milestones and retentions. The script is invoked using the Bash tool and operates purely on local input provided by the agent.
[EXTERNAL_DOWNLOADS]: The skill references and provides links to reputable Israeli legal and public information sites, including he.wikisource.org for statutes, nevo.co.il for consolidated regulations, and official government PDFs (olaw.org.il). These references are used for informational purposes and to verify regulatory thresholds.

israeli-renovation-scope-builder