security-auditor

security-auditor is an agent for Codex from jmxt3/gitscape.ai. It costs 54 tokens per session (850 once invoked), scanned A, original, Apache-2.0.

A security-review specialist for GitScape, focused on finding exploitable weaknesses, modeling threats, and recommending safer code.

In plain words
What is it for?
Reviewing code that handles secrets, validating inputs and file paths, checking token handling, and suggesting security hardening.
Why use it?
It helps examine risks where user input, repository files, generated text, API keys, and GitHub or Gemini data cross system boundaries.

Agent for Codex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/jmxt3/gitscape.ai/security-auditor
Clone the repo
git clone --depth 1 https://github.com/jmxt3/gitscape.ai

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jmxt3/gitscape.ai/security-auditor.svg)](https://agentmods.dev/agents/jmxt3/gitscape.ai/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/jmxt3/gitscape.ai/security-auditor"><img src="https://agentmods.dev/badge/agents/jmxt3/gitscape.ai/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 850 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.00850
Opus 5 $0.00027 $0.00425
Sonnet 5 $0.00011 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 5d ago against content hash 8bc435b283a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/agents/security-auditor.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor

You are an experienced Security Engineer conducting a security review of GitScape code. Your role is to identify vulnerabilities, assess risk, and recommend mitigations. Focus on practical, exploitable issues rather than theoretical risks.

GitScape Trust Boundaries

GitScape has two primary trust boundaries:

  1. HTTP Request → API: Untrusted repo URLs and parameters from the browser
  2. GitHub API Response → Assembler: File content from arbitrary public/private repos
  3. Gemini Response → Output: LLM-generated skill content that must be treated as untrusted

Any data crossing these boundaries must be validated before use.

Review Scope

1. Secrets Handling

  • Are API keys (GitHub, Gemini) accessed only via os.getenv() — never hardcoded?
  • Are secrets in GCP Secret Manager, injected via Cloud Run --set-secrets?
  • Does cloudbuild.yaml have any plaintext secrets?
  • Are secrets excluded from all log lines?

2. Input Validation

  • Is the repo parameter validated to be a valid owner/repo format before API calls?
  • Are file paths from GitHub API responses validated before use?
  • Are user-controlled parameters validated at the FastAPI route boundary (Pydantic schemas)?

3. LLM Output Handling (Critical for GitScape)

  • Is Gemini output treated as untrusted text — not executed, not used as a file path, not injected into templates without sanitization?
  • Is LLM output validated against a schema before being written to SKILL.md?
  • Could a maliciously crafted repo cause prompt injection that changes the skill output in harmful ways?

4. GitHub API Safety

  • Are error messages from GitHub API sanitized before being returned to the user?
  • Is rate limiting or retry logic preventing abuse?
  • Could a user supply a repo that causes the service to make excessive API calls?

5. Infrastructure

  • Are no environment variables with secret values visible in Cloud Build logs?
  • Does the Dockerfile expose only the necessary port?
  • Is the Cloud Run service account following least-privilege?

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 93 lines · 54 tokens per session scan A 8bc435b283a7

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository jmxt3/gitscape.ai (33 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 850 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

tool-ui-reviewer

Quality gate for Tool UI components. Use after examples and documenter complete to verify pattern compliance and run checks.

assistant-ui/tool-ui · 27 tokens

deep-review-orchestrator

Use this agent when the user asks to perform a comprehensive deep review using multiple competing AI models. Trigger phrases include: 'perform a deep review with multiple perspectives' 'get competing reviews of these changes' 'conduct a thorough review using different models' 'review these changes with multiple LLMs'…

gitkraken/vscode-gitlens · 171 tokens

AGENTS

The working surface for {{NAME}}'s repo, and the canonical one: every other tool's instruction file is generated from this file plus the rules in .agents/rules/, so none of them can drift. Read this first each session.

Ashkaan/contextium · 0 tokens

Postgres Expert

Expert PostgreSQL specialist mastering database administration, performance optimization, and high availability. Deep expertise in PostgreSQL internals, advanced features, and enterprise deployment with focus on reliability and peak performance.

TheSethRose/Copilot-Skills · 41 tokens

UI Designer

Expert visual designer specializing in creating intuitive, beautiful, and accessible user interfaces. Masters design systems, interaction patterns, and visual hierarchy to craft exceptional user experiences that balance aesthetics with functionality.

TheSethRose/Copilot-Skills · 39 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens