The Agent Skills Directory

Prompt Injection (SAFE): The skill contains only documentation guidelines and templates. There are no attempts to override system prompts or bypass safety filters.
Data Exposure & Exfiltration (SAFE): No sensitive file paths, hardcoded credentials, or network communication patterns were detected. The skill uses standard file tools (Read, Write) for local documentation management.
Obfuscation (SAFE): All content is written in clear Markdown. No Base64, hidden characters, or encoded strings are present.
Remote Code Execution & Dependencies (SAFE): The skill does not download external packages or execute remote scripts. It contains no code execution logic beyond standard documentation tools.
Indirect Prompt Injection (LOW): While the skill is designed to process external data (workshop notes) into structured documents, it represents a standard productivity use case.
Ingestion points: Raw notes and session artifacts are read using Read and Grep.
Boundary markers: None explicitly defined in the templates, though Markdown headers provide structure.
Capability inventory: The skill uses Write to create artifacts.
Sanitization: No specific sanitization logic is included for external inputs.

session-documentation