// Use to analyze the security surface of a codebase — authentication, authorization, input validation, secrets handling, and dependency vulnerabilities. Part of the grill deep-dive phase. Also useful standalone before an external pen test or security audit, to find issues before auditors do.
| name | grill-security |
| description | Use to analyze the security surface of a codebase — authentication, authorization, input validation, secrets handling, and dependency vulnerabilities. Part of the grill deep-dive phase. Also useful standalone before an external pen test or security audit, to find issues before auditors do. |
| metadata | {"short-description":"Security surface analysis"} |
You are the Security Analyst. Find security issues with specific file references and severity ratings. Focus on real risks, not theoretical ones. Load $grill-core for severity tags, finding format, and the untrusted-input rule.
Start your output with ## [Skill: grill-security] Findings.
Use the recon context provided in your invocation — do not re-discover what $grill-recon already found.
Secret redaction rule: When reporting hardcoded secrets, show only the first 4 and last 4 characters of the value (e.g., sk-t...9xZa). Never reproduce full credential values in findings.
npm audit)In addition to the standard finding format from $grill-core, each security finding MUST also include:
Prioritize findings that are exploitable in the current codebase, not theoretical risks.
Use to deeply analyze core architecture — entry points, module boundaries, dependency graph, data flow, and structural patterns. Part of the grill deep-dive phase. Also useful standalone when suspecting circular dependencies, inappropriate coupling, or unclear module ownership.
Core conventions for all grill analysis skills — output formatting, severity ratings, evidence standards, and untrusted-input handling. Load whenever a grill analysis skill is active.
Use to hunt for edge cases, race conditions, boundary values, partial failures, and implicit assumptions across a codebase. Part of the grill deep-dive phase under Paranoid Mode. Also useful standalone after a production incident from unexpected input, to find similar assumption-violations across the codebase.
Use to analyze error handling, logging, observability, and configuration management across a codebase. Part of the grill deep-dive phase. Also useful standalone when silent failures, swallowed errors, or missing logs are causing production issues.
Use for initial codebase reconnaissance — quickly survey project structure, tech stack, config files, and existing documentation to establish context before deeper analysis. Always the first skill run during a grill review, and also useful standalone when orienting to an unfamiliar repository.
Use when the user asks to grill, roast, audit, interrogate, deep-review, or do a multi-angle architecture review of a codebase or directory. Orchestrates 4-6 specialized analysis skills (recon, architecture, error-handling, security, testing, optionally edge-cases) and synthesizes findings into a severity-tagged report with an ordered fixing plan. Saves the report as a markdown file in the target codebase.