securitylisted
Install: claude install-skill n-n-code/n-n-code-skills
# Security
Find and reduce realistic abuse paths while keeping evidence, authority, and
side effects explicit.
Compose with `security-identity-access` when identity or tenant-authorization
boundaries are central. That companion owns identity-specific checks; this
skill owns the shared investigation, safety, evidence, and reporting contract.
## Choose The Mode And Authority
| Mode | Use when | Authority |
|---|---|---|
| `security review` | Determine whether concrete code, configuration, or a change creates security-relevant weaknesses or unsafe exposures | Read-only: do not edit source or configuration or change external state |
| `threat model` | Map assets, boundaries, attacker goals, abuse paths, and mitigations | Read-only: do not edit the system or present scenarios as confirmed vulnerabilities |
| `secure implementation` | Design, implement, or remediate security-sensitive behavior | Mutate only the files or systems explicitly authorized by the request |
Writing an explicitly requested report does not authorize remediation. If a
request combines analysis and implementation, keep the initial investigation
read-only and make the transition to changes visible.
## Shared Workflow
1. **Set scope and assumptions.** Identify the mode, target paths and
environments, protected assets, plausible attacker capabilities, deployment
shape, and relevant authorization assumptions. Inspect discoverable context
before asking questions; ask only when an answer would materi