agentsclimarketplace

Wick security review

Skill agoradynamics/wick/.claude/skills/wick-security-review

Drop-in thinking-partner personality layer for Claude Code, Cursor, ChatGPT, and 20+ AI agent runtimes. MIT. Plaintext. Persistent memory. Framework-grounded. Calibration-disciplined.

Install
npx -y skills add agoradynamics/wick --skill wick-security-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

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.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, as published. Nobody here has run it

Wick — Security Review

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

  1. Input validation — user input reaching DB, shell, eval, rendering without sanitization
  2. Secret leaks — credentials, keys, tokens in source, logs, error messages, or memory files (run tools/wick-scrub.mjs)
  3. Auth/authz flaws — missing auth checks, IDOR, privilege escalation paths, session fixation
  4. Injection vectors — SQL, command, prompt, XSS, SSRF, XXE, deserialization
  5. Crypto misuse — hardcoded keys, weak algorithms, predictable randomness, ECB mode, constant-time failures
  6. Dependency risks — outdated packages with known CVEs, supply-chain surface, typosquatting risk
  7. Error handling that leaks — stack traces to users, verbose DB errors, timing oracles
  8. 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.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.