The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill uses Glob and Grep tools to search for existing StoreKit implementations in the project's codebase (e.g., searching for import StoreKit in files matching **/*Store*.swift). This analysis of external, potentially untrusted source code creates a surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Local Swift source files containing StoreKit keywords, identified via Glob and Grep commands in the SKILL.md pre-generation checks.
Boundary markers: The instructions lack explicit delimiters or safety prompts to ensure the agent ignores embedded instructions within the files it reads.
Capability inventory: The skill utilizes Read, Write, Edit, and Bash tools, which provides a significant capability set if an injection were to be successful.
Sanitization: Content retrieved from project files is processed directly without sanitization or validation against a strict schema.

paywall-generator