spectra-auditlisted

Audit changed code for security sharp edges in a Claude Code fork. This generated skill is report-only: it SHALL NOT edit files and SHALL NOT apply fixes directly inside the fork. ## Claude fork context Run `git diff HEAD` to gather the current changes. If there are no changes, report that no security sharp edges were found and stop. Analyze the diff through the Scoundrel, Lazy Developer, and Confused Developer lenses. Return a consolidated report with findings grouped by severity, affected files, and recommended fixes. The main thread decides whether to apply any fixes. --- ## Core Framework ### Three Adversaries | Role | Mindset | Key Questions | | ---------------------- | ----------------------------------------- | --------------------------------------------------------------------------------- | | **Scoundrel** | Malicious, deliberate exploitation | Can I disable security via config? Downgrade algorithms? Inject values? | | **Lazy Developer** | Copy-paste, skips docs, deadline pressure | Is the first example safe? Is the default secure? Do errors guide me right? | | **Confused Developer** | Misunderstands usage | Can I swap params silently? Will mistakes fail loudly? Are types distinguishable? | ### Six Trap Categories #### 1. Algorithm Choice Traps Letting developers choose algorithms =