The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and recommend patterns based on project source code using tools like Read, Grep, and Glob. This introduces an attack surface where malicious instructions embedded in the analyzed code could potentially influence the agent's behavior.\n
Ingestion points: Project source code files (e.g., controllers, views, and JavaScript files) accessed via the Read, Grep, and Glob tools.\n
Boundary markers: The skill does not define specific delimiters or instructions to the agent to treat analyzed code as untrusted data or to ignore embedded instructions.\n
Capability inventory: The skill allows for code analysis and recommendation but does not include high-privilege tools like arbitrary shell execution or broad network access.\n
Sanitization: There is no evidence of sanitization or filtering applied to the data ingested from project files before it is processed by the agent.

hotwire-patterns