The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements a 'STOP PROTOCOL' using high-authority instructional language such as '절대 위반 금지' (must not violate) and '최우선 규칙' (highest priority rule). This is used for user experience flow control to prevent the agent from skipping educational steps, rather than bypassing safety filters.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its documentation retrieval process.
Ingestion points: External documentation fetched via curl and local markdown files in the references/ directory.
Boundary markers: No specific delimiters or 'ignore instructions' warnings are defined for the fetched external content.
Capability inventory: Access to curl, file system read tools, and user interaction via AskUserQuestion.
Sanitization: No explicit sanitization or validation of the fetched external documentation is performed before processing.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to use curl to fetch official documentation from external URLs. This is documented as a functional requirement to provide accurate information and avoid the loss of detail associated with LLM summarization of web content.

day1-onboarding