The Agent Skills Directory

[SAFE]: The skill operates as a static analysis and verification planning tool. It is explicitly prohibited from writing or modifying code, which prevents unauthorized system changes.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions emphasize evidence-based reporting with mandatory citations of source files and line numbers.
[SAFE]: External references are limited to well-known technology documentation and legitimate software testing frameworks such as Cucumber, Hypothesis, and fast-check.
[SAFE]: The skill includes comprehensive guardrails (references/llm-verification-guardrails.md) that enforce an 'evidence-first' reasoning chain and confidence gating to prevent the model from inflating verdicts or hallucinating implementation details.

attest