The Agent Skills Directory

[SAFE]: The skill implements a standard design guideline retrieval system. No malicious code, unauthorized network access, or sensitive data exposure patterns were identified.
[PROMPT_INJECTION]: The skill uses strong instructional markers such as "CRITICAL PREREQUISITE" and "MUST ONLY" to define intent recognition and tool scoping. These instructions are used to ensure the agent only invokes the design tool when explicitly requested and do not attempt to bypass safety filters or override system instructions.
[DATA_EXFILTRATION]: No sensitive file paths, credential harvesting patterns, or network exfiltration commands (like curl or wget) were found in the skill files.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill instructs the agent to use text returned from the get_guidelines tool as instructions for subsequent batch_design tool calls.
Boundary markers: None are explicitly defined in the instructions for the agent when processing the tool output.
Capability inventory: The skill is part of a design workflow that includes executing the batch_design tool.
Sanitization: There are no instructions for the agent to sanitize or validate the content returned by the external tool before following its instructions.

pencil-mcp-get-guidelines