drift: Skill for Claude Code

.github/skills/drift-security-triage/SKILL.md

drift-security-triage is a skill for Claude Code from mick-gsk/drift. It costs 33 tokens per session (881 once invoked), scanned A, original, MIT.

A workflow for reviewing vulnerability reports and security alerts in the Drift repository. It covers GitHub Security Advisories, private reports, Dependabot alerts, CodeQL findings, and detect-secrets findings.

In plain words
What is it for?
Use it to assess incoming reports, check whether Drift parses or executes code, evaluate network-related risk, and classify findings according to the repository’s security rules.
Why use it?
It helps distinguish real security problems from issues that require access the attacker would already have, while checking how Drift handles code and network access.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

This is mick-gsk/drift's own configuration. It tells Claude Code how to work on drift itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything drift configures →

Part of the drift plugin — 31 skills, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to mick-gsk/drift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mick-gsk/drift/main/.github/skills/drift-security-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mick-gsk/drift

Made for: Claude Code.

Or install drift, the plugin that ships this one along with the rest of its 31 skills, 17 agents.

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 drift-security-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/drift-security-triage/github.svg)](https://agentmods.dev/skills/mick-gsk/drift/drift-security-triage)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-security-triage"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-security-triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for drift-security-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-security-triage"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-security-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00033 $0.00881
Opus 5 $0.00016 $0.00441
Sonnet 5 $0.00007 $0.00176
Haiku 4.5 $0.00003 $0.00088

Measured 9d ago against content hash 820cacf10372, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

drift-security-triage 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 9d 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.

.github/skills/drift-security-triage/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Security Triage Skill

Purpose

Guide Copilot agents through consistent, policy-aligned triage of security reports for the drift repository.

When to Use

  • Evaluating a new GitHub Security Advisory (GHSA)
  • Triaging a vulnerability report submitted via email or private advisory
  • Assessing Dependabot security alerts
  • Responding to CodeQL or detect-secrets findings

Triage Workflow

Step 1: Trust Model Check

Drift operates under the same trust level as local shell access. Before classifying severity, determine:

  1. Does the vulnerability require prior write access to the target repository? → If YES: likely out of scope (attacker already has equal privileges).

  2. Does drift execute any analyzed code? → No. drift uses ast.parse() and tree-sitter for parsing — no code execution.

  3. Does drift make network requests? → No. drift is fully local — no exfiltration vector exists.

Step 2: Out-of-Scope Classification

The following are explicitly NOT vulnerabilities in drift (see SECURITY.md):

Category Reason
Malicious source files causing misleading findings Same trust boundary — attacker already has write access
Resource exhaustion on huge repositories Operational concern, not a vulnerability
Static analysis false positives Signal quality issue — use false-positive template
Secret-scanning baseline entries Intentional test fixtures with non-reversible hashes
Git history tampering History integrity is the repo owner's responsibility

If the report matches any of these → respond with the out-of-scope template (Step 5).

Step 3: Severity Assessment

For in-scope vulnerabilities, assess using CVSS v3.1 principles:

Factor drift-specific consideration
Attack vector Always Local (drift requires file system access)
Privileges required At minimum Low (read access to target repo)
User interaction Typically Required (user must invoke drift)
Scope Unchanged (drift cannot escape its process boundary)
Confidentiality drift reads files user already has access to — typically None
Integrity drift produces reports — at most Low (misleading output)
Availability Resource exhaustion possible — Low to Medium

Read the full file on GitHub · 109 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. 9d ago First seen · 109 lines · 33 tokens per session scan A 820cacf10372

Subscribe to this mod's changes

drift-security-triage is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 881 once invoked, about $0.0002 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 skills, from other repositories

dispatcher

Use this skill when running a Taniwha build from the main Claude Code session. The skill turns the main session into a thin, mechanical executor that follows instructions from ephemeral orchestrator subagents. Trigger this whenever the user wants to start a Taniwha build, resume an interrupted one, or work on a…

taniwhaai/arai · 153 tokens

contract-derivation

Use this skill after a design document exists and before any module is implemented. It takes a design doc and derives per-module contracts (manifests) that are complete enough for an implementor working in isolation to build each module correctly without seeing the rest of the system. Trigger this whenever the user…

taniwhaai/arai · 134 tokens

design-doc

Use this skill before writing any non-trivial code, especially when starting a new feature, service, or codebase. It produces a structural design document that commits to module boundaries, contracts, and data shapes BEFORE implementation begins. Trigger this whenever the user describes building something new, asks to…

taniwhaai/arai · 137 tokens

verifier

Use this skill when verifying that a completed Taniwha implementation or composition satisfies its contract's acceptance criteria. The verifier reads the contract, the implementation's source files, and the project context, then writes its own tests against the contract's acceptance criteria, runs them, and reports…

taniwhaai/arai · 122 tokens

composition

Use this skill when wiring two completed modules together to satisfy a parent contract, especially in a compartmentalised setting. Trigger this whenever the user has two implemented modules (each with its manifest) and a parent contract that says how they should compose, when the user asks to "compose these modules"…

taniwhaai/arai · 136 tokens

leaf-implementation

Use this skill when implementing a single module against a contract manifest, especially in a compartmentalised setting where the implementor should NOT see the rest of the system. Trigger this whenever a manifest exists and the user wants to implement that module, asks to "implement this module", "build against this…

taniwhaai/arai · 133 tokens