The Agent Skills Directory

[Prompt Injection] (SAFE): No attempts to override agent behavior or bypass safety constraints were found. The instructional style is standard for skill development.- [Data Exposure] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected.- [Remote Code Execution] (SAFE): The skill does not download, install, or execute external scripts or packages.- [Command Execution] (SAFE): No system-level commands, privilege escalation, or persistence mechanisms are utilized.- [Obfuscation] (SAFE): The content is clear and readable, with no evidence of Base64 encoding, zero-width characters, or homoglyph attacks.- [Indirect Prompt Injection] (SAFE): The skill ingests user story ideas into markdown notes. While this represents a data ingestion surface, the skill lacks dangerous execution capabilities (like eval or subprocess calls) that could be exploited by malicious narrative content. Boundary markers like and tags are used to organize output.

cw-brainstorming