The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user's project files to extract deployment logic and dependencies.
Ingestion points: Solidity files in the src/ and script/ directories are scanned and read using the Glob tool as described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings to wrap the processed source code content.
Capability inventory: The skill possesses the capability to read local files and generate or modify executable Foundry deployment scripts.
Sanitization: The skill mitigates this surface by requiring the user to confirm a summary table of all extracted parameters before any scripts are generated.
[EXTERNAL_DOWNLOADS]: The generated deployment scripts utilize an external library from the skill author's official repository.
Reference: The scripts inherit from BCScript in the cyfrin/battlechain-lib repository, which is a legitimate resource provided by the vendor.

battlechain-tutorial