Wick — Security Review
Updated: 2026-04-20 · first written 2026-04-20
Security-specific review lens. Focused on what can be exploited, not on what's merely ugly.
When to invoke
- Before shipping to production
- After adding auth, crypto, or third-party integrations
- Reviewing a PR touching user input, data storage, or network boundaries
- When a security-sensitive dependency is added or updated
- After a relevant CVE disclosure in your stack
What Wick looks for
- Input validation — user input reaching DB, shell, eval, rendering without sanitization
- Secret leaks — credentials, keys, tokens in source, logs, error messages, or memory files (run
tools/wick-scrub.mjs)
- Auth/authz flaws — missing auth checks, IDOR, privilege escalation paths, session fixation
- Injection vectors — SQL, command, prompt, XSS, SSRF, XXE, deserialization
- Crypto misuse — hardcoded keys, weak algorithms, predictable randomness, ECB mode, constant-time failures
- Dependency risks — outdated packages with known CVEs, supply-chain surface, typosquatting risk
- Error handling that leaks — stack traces to users, verbose DB errors, timing oracles
- Agentic-specific (OWASP Agentic Top 10) — prompt injection, tool misuse, memory poisoning, unchecked tool output, excess agency, supply-chain via model/plugin
Output format
## CRITICAL (ship-blocking)
- [file:line] Issue, exploit scenario, fix
## HIGH
- [file:line] Issue, impact, fix
## MEDIUM / LOW
- [file:line] Issue, hardening recommendation
## Recommended followups
- Run `tools/wick-scrub.mjs` on memory/ and repo before push
- Consider [specific hardening measure] as a follow-up
Framework grounding
Preparation-for-adversity, weaponized — imagine an adversary has already gotten in. What do they see? What can they reach? Inversion (Munger) — "how would I guarantee compromise?" Three-framework convergence (threat model + code + dependency scan) for high-confidence findings.
Scope limits
This skill is a well-read generalist's first-pass review. It does not replace:
- Professional penetration testing
- SAST/DAST automated scanners
- Formal threat modeling (STRIDE, PASTA)
- Compliance audits (SOC 2, HIPAA, PCI)
If the stakes warrant those, name them explicitly in the output so the user doesn't mistake this review for the real audit.
1---2name: wick-security-review3description: Security-focused code review — OWASP Top 10, secret leaks, auth flaws, injection, crypto misuse, dependency risk, and agentic-specific threats (prompt injection, memory poisoning). Use before production ship or after security-sensitive changes.4license: MIT5---67# Wick — Security Review89*Updated: 2026-04-20 · first written 2026-04-20*1011Security-specific review lens. Focused on what can be *exploited*, not on what's merely ugly.1213## When to invoke1415- Before shipping to production16- After adding auth, crypto, or third-party integrations17- Reviewing a PR touching user input, data storage, or network boundaries18- When a security-sensitive dependency is added or updated19- After a relevant CVE disclosure in your stack2021## What Wick looks for22231. **Input validation** — user input reaching DB, shell, eval, rendering without sanitization242. **Secret leaks** — credentials, keys, tokens in source, logs, error messages, or memory files (run `tools/wick-scrub.mjs`)253. **Auth/authz flaws** — missing auth checks, IDOR, privilege escalation paths, session fixation264. **Injection vectors** — SQL, command, prompt, XSS, SSRF, XXE, deserialization275. **Crypto misuse** — hardcoded keys, weak algorithms, predictable randomness, ECB mode, constant-time failures286. **Dependency risks** — outdated packages with known CVEs, supply-chain surface, typosquatting risk297. **Error handling that leaks** — stack traces to users, verbose DB errors, timing oracles308. **Agentic-specific (OWASP Agentic Top 10)** — prompt injection, tool misuse, memory poisoning, unchecked tool output, excess agency, supply-chain via model/plugin3132## Output format3334```35## CRITICAL (ship-blocking)36- [file:line] Issue, exploit scenario, fix3738## HIGH39- [file:line] Issue, impact, fix4041## MEDIUM / LOW42- [file:line] Issue, hardening recommendation4344## Recommended followups45- Run `tools/wick-scrub.mjs` on memory/ and repo before push46- Consider [specific hardening measure] as a follow-up47```4849## Framework grounding5051Preparation-for-adversity, weaponized — imagine an adversary has already gotten in. What do they see? What can they reach? Inversion (Munger) — "how would I guarantee compromise?" Three-framework convergence (threat model + code + dependency scan) for high-confidence findings.5253## Scope limits5455This skill is a well-read generalist's first-pass review. It does **not** replace:56- Professional penetration testing57- SAST/DAST automated scanners58- Formal threat modeling (STRIDE, PASTA)59- Compliance audits (SOC 2, HIPAA, PCI)6061If the stakes warrant those, name them explicitly in the output so the user doesn't mistake this review for the real audit.
agoradynamics