The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or supporting files. The skill is dedicated to technical writing and structured design specification.
[DATA_EXFILTRATION]: The skill contains instructions to read local code to identify architectural constraints. This access is limited to the purpose of design documentation and does not involve any network commands or mechanisms for exfiltrating data.
[PROMPT_INJECTION]: Regarding indirect prompt injection surfaces (Category 8):
Ingestion points: The skill consumes external Product Requirements Documents (PRDs) provided in the conversation or as files (SKILL.md).
Boundary markers: The skill does not define explicit delimiters or 'ignore' warnings for the input PRD content.
Capability inventory: The skill's capabilities are limited to reading local files for context and writing Markdown or JSON Schema files. It has no access to network tools, shell command execution, or dynamic code evaluation.
Sanitization: No explicit validation or sanitization is performed on the ingested PRD data. The risk remains low because the skill's operations are confined to a rigid 10-section document generation process.

solution-design