The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest and process unstructured data from external, untrusted sources such as social media and community forums, creating a surface for indirect prompt injection. Ingestion points: Customer feedback is gathered from surveys, support tickets, and social media. Boundary markers: The skill does not define specific delimiters or instructions to isolate processed feedback from agent instructions. Capability inventory: The workflows describe data aggregation and reporting tasks which could be influenced by malicious content. Sanitization: No input validation or sanitization steps are defined in the instructions.
[NO_CODE]: The skill consists entirely of natural language instructions and markdown templates with no executable scripts or code provided within the skill package.

Feedback Analyzer