The Agent Skills Directory

[PROMPT_INJECTION]: The 'Agent Workflow (MANDATORY)' section uses strong directive language to prescribe a specific multi-agent setup using the TeamCreate tool. While this overrides default agent behavior to enforce a particular development process, it is focused on task orchestration and codebase exploration rather than bypassing safety filters or security protocols.
[EXTERNAL_DOWNLOADS]: The skill references the framer-motion package (version 11), which is a standard and well-known animation library for React development.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it instructs the agent to process untrusted data from an external codebase.
Ingestion points: The skill utilizes Read, Glob, and Grep tools to examine existing code patterns in the local environment.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content found within the files it reads.
Capability inventory: The skill allows for Write and Edit operations, which could be exploited if the agent is successfully manipulated by malicious content in the codebase.
Sanitization: No automated sanitization or validation of the ingested code content is performed before the agent acts upon it.

interactive-states