agentsclimarketplace

Security

Skill jessedegans/jstack/skills/security

7 skills built from studying how Anthropic designs agents internally. ~700 lines, zero fluff.

Install
npx -y skills add jessedegans/jstack --skill security

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.
  • 0 stars0 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

Use when reviewing code for security vulnerabilities, before shipping to production, or when the user asks for a security audit. Runs OWASP Top 10 + STRIDE analysis with a strict false positive filter. Confidence gate at 8/10. No theoretical hand-waving.

SKILL.md

3.1 KB, 676 tokens by cl100k_base, as published. Nobody here has run it

Security Audit

The Scan

1. Map the attack surface

  • Grep for routes, auth handlers, external integrations, file uploads, admin endpoints
  • List all entry points (API routes, webhooks, scheduled jobs, CLI commands)

2. OWASP Top 10 pass

For each entry point, check:

CategoryLook for
A01 Broken Access ControlMissing auth checks, direct object references, path traversal
A02 Crypto FailuresWeak algorithms, hardcoded secrets, plaintext storage
A03 InjectionSQL, command, template, LLM prompt injection
A04 Insecure DesignBusiness logic flaws, missing rate limits
A05 MisconfigurationDebug mode, default creds, overly permissive CORS
A06 Vulnerable ComponentsOutdated deps with known CVEs
A07 Auth FailuresWeak passwords, missing MFA, session fixation
A08 Integrity FailuresUnsigned updates, untrusted CI/CD inputs
A09 Logging GapsMissing audit trail, logging sensitive data
A10 SSRFUser-controlled URLs fetched server-side

3. STRIDE per component

For each significant component: can an attacker achieve Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, or Elevation of Privilege?

4. Data classification

Tag all stored/transmitted data as:

  • RESTRICTED - credentials, PII, financial data
  • CONFIDENTIAL - internal business logic, configs
  • INTERNAL - non-sensitive but not public
  • PUBLIC - safe to expose

The Filter (the actually valuable part)

Hard exclusions, don't report these:

  1. DoS via resource exhaustion (unless trivially exploitable)
  2. Test-only code vulnerabilities
  3. Memory safety in memory-safe languages
  4. Log spoofing / log injection
  5. Missing CSP headers (unless XSS is also present)
  6. Theoretical timing attacks without proof
  7. Missing X-Frame-Options when CSP frame-ancestors is set
  8. Self-XSS (requires attacker to control own browser)
  9. Open redirects without auth token leakage
  10. Missing rate limiting on non-auth endpoints
  11. Verbose error messages in development mode
  12. Cookie without Secure flag on localhost
  13. Missing HSTS on internal-only services
  14. Theoretical ReDoS without proof of exploitable input
  15. Information disclosure via stack traces in dev mode

Precedents, assume these are fine unless proven otherwise:

  • UUIDs are unguessable
  • Environment variables are trusted
  • Client-side JS doesn't need server-side auth
  • ORM-generated queries are injection-safe
  • Framework CSRF protection works when enabled
  • HTTPS is enforced at infra level
  • Container isolation is effective
  • Cloud IAM roles are correctly scoped

Rules

  • Confidence gate: 8/10 minimum. If you're not at least 80% sure it's real, don't report it.
  • Every finding needs an exploit scenario. Step-by-step: what does the attacker do, what do they get? No hand-waving.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 327,069. 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.