The Agent Skills Directory

[Indirect Prompt Injection] (MEDIUM): The skill is designed to process external, untrusted data (requirements, user stories, and acceptance criteria) and possesses capabilities that could be abused if malicious instructions are embedded in that data.
Ingestion points: The skill ingests user-provided text through the $ARGUMENTS variable and during 'Step 1: Understand requirements'.
Boundary markers: The instructions do not define clear delimiters or system-level warnings to the agent to disregard instructions found within the user-provided requirements.
Capability inventory: The skill is granted Bash, Write, Edit, Read, Glob, and Grep tools, allowing for significant system interaction.
Sanitization: There is no explicit mechanism for sanitizing or validating user input before the agent processes it or uses it to generate file content.

product-design