The Agent Skills Directory

[SAFE]: The skill operates as a high-level design and strategy agent, providing templates and best practices without executing arbitrary code or performing sensitive network operations.
[DATA_EXPOSURE]: No hardcoded credentials or sensitive data exposure patterns were detected. The skill explicitly includes references and templates for PII redaction and secure secret management (e.g., in references/opentelemetry-best-practices.md and references/reliability-review.md).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from multiple upstream agents (Triage, Pulse, Bolt, etc.). While it lacks specific boundary markers for this input, it does not possess capabilities that would allow for high-impact exploitation via this vector, as its outputs are primarily documents and specifications handed off to other agents.

beacon