The Agent Skills Directory

Safe Resource Reference: The skill instructs the agent to read documentation from a local file path (external/ebpf-verifier/docs/llm-context.md). This is a legitimate way to provide context for diagnostic tasks within a development environment.
Data Ingestion Analysis: The skill processes untrusted user data, specifically eBPF source code and verifier logs. While this represents a potential surface for indirect prompt injection, the skill does not have any sensitive capabilities such as network access, file system writes, or shell execution that could be exploited.
Diagnostic Purpose: The instructions are focused on providing explanations and code fix recommendations to the user, ensuring the agent remains in an advisory role without autonomous risk.

verify-prevail