security-sweep

security-sweep is a skill for Claude Code from escoffier-labs/skillet. It costs 51 tokens per session (970 once invoked), scanned A, original, MIT.

A read-only review of a repository for security weaknesses and exposed sensitive information. It checks areas such as secrets, dependencies, input handling, login and permissions, and publicly reachable functionality.

In plain words
What is it for?
It is for security-auditing a project, checking dependencies for known vulnerabilities, finding leaked secrets, and recommending hardening work.
Why use it?
It helps reveal problems an attacker could use, including known vulnerable packages, unsafe input processing, missing permission checks, and leaked credentials. The input says it reports fixes but does not apply them.

Skill for Claude Code

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

Part of the skillet plugin — 39 skills, 1 hook shipped together

Good fit It is for security-auditing a project, checking dependencies for known vulnerabilities, finding leaked secrets, and recommending hardening work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/escoffier-labs/skillet/security-sweep
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.

Any agent
npx skills add escoffier-labs/skillet --skill security-sweep
Clone the repo
git clone --depth 1 https://github.com/escoffier-labs/skillet

Made for: Claude Code.

Or install skillet, the plugin that ships this one along with the rest of its 39 skills, 1 hook.

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-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/escoffier-labs/skillet/security-sweep/github.svg)](https://agentmods.dev/skills/escoffier-labs/skillet/security-sweep)
Your own site
<a href="https://agentmods.dev/skills/escoffier-labs/skillet/security-sweep"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/security-sweep/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 security-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/escoffier-labs/skillet/security-sweep"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/security-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 970 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 $0.00051 $0.00970
Opus 5 $0.00026 $0.00485
Sonnet 5 $0.00010 $0.00194
Haiku 4.5 $0.00005 $0.00097

Measured 10d ago against content hash 9a465063d3cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

security-sweep 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 10d 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.

skillet/skills/security-sweep/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

security-sweep

A defensive security audit of a repository: find what an attacker could use, report how to fix it. Every finding ships with its remediation; nothing in the report teaches exploitation beyond what is needed to verify the fix.

Read-only, with one exception: never copy, log, or echo discovered secret values anywhere, including the report. Reference secrets by file:line and type only.

Lenses

Lens Hunting for
Secrets Credentials, tokens, API keys, private keys in the working tree AND full git history (git log --all -p with pattern grep); high-entropy strings in config
Dependencies Known CVEs (npm audit, pip-audit, govulncheck, cargo audit as applicable), abandoned packages, pinning hygiene, lockfile present
Input handling Injection surfaces (SQL, shell, path traversal, template), missing validation at trust boundaries, unsafe deserialization
AuthN/AuthZ Unprotected routes and endpoints, missing authorization checks distinct from authentication, weak hashing, session handling
Exposure Destructive endpoints reachable without auth (a DELETE route an agent or crawler can hit), debug modes, verbose errors leaking internals, internal hostnames/private IPs/PII in code and docs

Lens guidance:

  • Secrets in history are findings even when the tree is clean; remediation is rotation first, history rewrite second (the publish-readiness skill has the full rewrite recipe).
  • For exposure, think about non-human callers too: anything with an OpenAPI spec and an unprotected destructive route will eventually be called by an automated agent.

Verification

Confirm before reporting: trace the path from untrusted input to the sink, or confirm the dependency version is actually in the resolved lockfile, or confirm the route really lacks the auth middleware (read the router, not just the handler). Findings that depend on configuration you cannot see get (unverified) and one severity lower. Do not write exploit payloads to prove findings; a traced code path is the proof.

Read the full file on GitHub · 77 lines

Files

What ships with it

2 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. 10d ago First seen · 77 lines · 51 tokens per session scan A 9a465063d3cb

Subscribe to this mod's changes

security-sweep is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 970 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

assess-interview-candidate

A structured hiring-assessment workflow that turns a candidate's résumé and a job description into reviewable evidence, interview questions, and an offline HTML report for interviewers.

dongshuyan/compass-skills · 129 tokens

task-clarifier

Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task…

dongshuyan/compass-skills · 74 tokens

user-profile-keeper

Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…

dongshuyan/compass-skills · 129 tokens

run-history-skill-builder

Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…

dongshuyan/compass-skills · 95 tokens

run-history-skill-upgrader

Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…

dongshuyan/compass-skills · 91 tokens

session-handoff-prompt

Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…

dongshuyan/compass-skills · 89 tokens