The Agent Skills Directory

[SAFE]: No security threats were identified. The skill performs standard text analysis and summarization tasks. Analysis for all 10 threat categories confirmed the absence of prompt injection, data exfiltration, or unauthorized code execution.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted conversation history. This risk is inherent to the skill's primary function. Ingestion points: Current conversation history and Google Drive files (SKILL.md). Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation. Capability inventory: The skill is designed to create Markdown and Word documents and search Google Drive files. Sanitization: No specific validation or escaping of conversation content is described in the provided files.

learning-capture