The Agent Skills Directory

[SAFE]: The skill contains no malicious code, unauthorized command execution, or obfuscation. Its primary function is to provide professional instructional guidance based on event industry research and established best practices.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external survey data, which is inherently untrusted. It effectively mitigates this vulnerability by providing explicit instructions for the agent to group free-text into themes, redact names from representatives quotes, and immediately route any code-of-conduct allegations to a specialized reporting pipeline rather than treating them as general survey findings.
[DATA_EXFILTRATION]: The skill handles data privacy defensively. It mandates that anonymity posture be established before collection, distinguishes between anonymous and confidential promises, and implements strict boundaries for how findings are handed off to different organizational roles to prevent the unauthorized exposure of raw participant data.

event-feedback