coding-security

A guide for checking a specific code path for security weaknesses where untrusted input crosses into sensitive operations. It covers areas such as login permissions, tenant separation, secrets, unsafe parsing, injection, and external requests.

In plain words
What is it for?
Use it to audit or harden code that handles attacker-controlled data, authentication, authorization, user or tenant ownership, secrets, interpreters, file or network boundaries, redirects, deserialization, or third-party dependencies.
Why use it?
It helps connect a possible weakness to a realistic attacker path and the protected operation at risk. This avoids treating a dangerous-looking line of code as a vulnerability without checking how it can actually be reached and abused.

Skill for Claude CodeCodex

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 skills/evoelsewhere/evoflux/coding-security
Any agent
npx skills add evoelsewhere/evoflux --skill coding-security
Clone the repo
git clone --depth 1 https://github.com/evoelsewhere/evoflux

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 967 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 $0.00070 $0.00967
Opus 5 $0.00035 $0.00483
Sonnet 5 $0.00014 $0.00193
Haiku 4.5 $0.00007 $0.00097

Measured yesterday against content hash d988b5f936fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-security 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 yesterday.

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.

app/agent/builtin_skills/coding-security/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Secure a code path

Model the reachable attacker and protected operation before enumerating vulnerability categories. Never treat a dangerous-looking primitive as an exploit without tracing control and impact. Do not load bundled references when this skill activates.

Establish the security boundary

  1. Identify assets, actors, credentials, trust zones, entry points, privilege transitions, and the exact operation being protected.
  2. Define authorization invariants at the resource and action boundary, including object ownership, tenant isolation, role changes, replay, and confused-deputy behavior.
  3. Trace attacker-controlled data through parsing, normalization, validation, policy checks, persistence, rendering, logging, and outbound calls.
  4. Read references/threat-boundary-checklist.md when the path crosses tenants, interpreters, file/network boundaries, redirects, deserializers, privileged workers, or third-party dependencies.

When the source, sink, or policy boundary is known only by behavior, route, error, field, or API text, call code_context with action="search" once to locate its declared identifier. Skip search when exact source identifiers are already known.

Use code_context on exact identifiers to bound the trust path: callers for reachable entry sites, callees for sensitive sinks, references for registration or callback wiring, and impact for upstream exposure. Start at depth 1. Static relationships support reachability analysis but never replace runtime authorization, data-flow, or exploit evidence. Once the boundary exposes an exact source and sink relationship, make the graph the next structural observation instead of continuing broad grep.

Keep refresh=true for the first indexed query and after edits. Use refresh=false only for an immediate follow-up that intentionally reuses the same index version.

Read references/code-context-contract.md for ambiguity, cross-repository limits, and dynamic-wiring fallbacks only after the graph reports such a gap.

Read the full file on GitHub · 95 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 95 lines · 70 tokens per session scan A d988b5f936fb

Subscribe to this mod's changes

coding-security is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 70 tokens to every session and 967 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 2026-08-31.

Related

Other skills, from other repositories

kane-cli

Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…

LambdaTest/kane-cli · 159 tokens

control-chrome

Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.

rojim666/SztuCode · 40 tokens

recent-release

Render Rove's recent releases as a self-contained, Rove-styled HTML page (Chinese by default). Reads shipped notes from packages/kobe/CHANGELOG.md + git tags, filters to user-facing changes, and emits one standalone .html file in the claude theme (terracotta on near-black, JetBrains Mono, terminal chrome). Use when…

Sma1lboy/rove · 112 tokens

yutori-scout

Set up continuous web monitoring with Yutori Scouts. Use when the user wants to track news, competitors, product updates, funding rounds, price changes, or any recurring web information.

yutori-ai/yutori-mcp · 43 tokens

yutori-computer-use

Run local Mac desktop tasks with Yutori computer use. Use when the user wants to operate macOS apps, websites in a local browser, or cross-app workflows on the visible desktop.

yutori-ai/yutori-mcp · 45 tokens

plan-review-triggers

Required reading whenever drafting any multi-step proposal, implementation plan, refactor approach, or response containing file paths and decision points. Use BEFORE writing any response that lists 3+ file paths, 2+ option-tradeoffs, a "Plan:"/"Steps:"/"Concrete changes:" section, or ends with "OK to proceed?" /…

ndom91/open-plan-annotator · 199 tokens