The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is entirely instructional and uses markdown files to define communication patterns and quality standards.- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized data access patterns were identified. The skill focuses on processing business messages without interacting with sensitive system configurations.- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code execution, script downloads, or package installations. It relies solely on local markdown references.- [PROMPT_INJECTION]: The instructions do not contain patterns intended to bypass AI safety filters or override core agent behavior. The guidelines focus on maintaining accuracy and integrity in message delivery.- [INDIRECT_PROMPT_INJECTION]: The skill ingests 'approved answers' and 'evidence' from external context. While this is a data ingestion surface, the skill has no dangerous capabilities (such as shell access, file-write, or network operations) that could be exploited via malicious input. It explicitly instructs the agent to preserve the evidence boundary and approved claims.

communicate-consulting-message