The Agent Skills Directory

[SAFE]: The skill contains instructional logic and reference materials to guide an agent's questioning process. No malicious patterns such as data exfiltration, obfuscation, or persistence were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as its primary function involves processing untrusted external data (such as user specifications, code files, and conversation history) to generate questions.\n
Ingestion points: Processes user-provided specifications, file contents, and conversation history.\n
Boundary markers: No specific delimiters or safety instructions are defined to separate external content from instructions.\n
Capability inventory: Utilizes the AskUserQuestion tool and instructions for agent delegation (forking).\n
Sanitization: No explicit sanitization or filtering of external content is specified.\n- [EXTERNAL_DOWNLOADS]: The README.md provides an installation command pointing to the author's GitHub repository. This is a standard installation procedure for the user and does not represent a runtime security risk for the agent.

ask-questions