Index of every page on this site: llms.txt
All skills
dominiktobureto avatar

/security-audit

@9125e02
Run it yourself

Use for security review, auth/permission changes, secrets, dependency risk, injection, SSRF, XSS, CSRF, data exposure, unsafe hooks, or supply-chain concerns.

Use this Skill: https://skilld.dev/gh/dominiktobureto/awesome-grok-build/security-audit

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈44 tokens for metadata: the name and description. ≈385 when used: this file.

Description uses 2.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈175 characters, or 2.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Security Audit

Find exploitable paths and prevent unsafe agent changes.

Grok Build Mode

  • Start in Plan Mode for any fix that touches auth, permissions, crypto, payments, secrets, or infrastructure.
  • Use subagents for threat tracks:
    • authz: object ownership, roles, tenant boundaries.
    • input: injection, XSS, SSRF, deserialization, path traversal.
    • secrets: env files, logs, tokens, CI config.
    • supply-chain: dependencies, hooks, install scripts.
  • Arena-style validation: require independent agreement for high-severity findings or reproduce with concrete evidence.
  • Human-in-the-loop: do not run destructive security tooling or exploit production systems.

Workflow

  1. Define assets, trust boundaries, and attacker goal.
  2. Inspect code paths that cross boundaries.
  3. Look for concrete exploitability, not generic fear.
  4. Propose minimal fixes with tests.
  5. Run security-relevant tests or static checks when available.
  6. Summarize residual risk.

Findings

[P1] Title
Asset:
Attack path:
Evidence:
Impact:
Fix:
Test:

Guardrails

  • Never print secrets.
  • Do not add dependencies for security scanning without approval.
  • Do not weaken auth checks to make tests pass.
  • Treat third-party skills and hooks as untrusted code until reviewed.

Example Prompts

Use security-audit. Review this auth diff for tenant-boundary bypasses and missing regression tests.
Audit `.grok/skills` and hooks for supply-chain or prompt-injection risks before I install them.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    The skill provides a framework for performing security audits and appears to be safe for use. It includes guardrails against leaking secrets, requires human oversight for destructive actions, and emphasizes independent verification of findings.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: LOW · No issues

Signed by skilld at 9125e02. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 6 months ago
version
1.0.0
author
awesome-grok-build

README badge

README badge for dominiktobureto/awesome-grok-build/security-audit